© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9184
    Prev
    Next
    INDEX
    Explanations

    mentions of songs or episodes in TV shows

    oai_token-act-pair · gemini-2.0-flash

    technical terms or keywords

    np_token-act-pair-logits · gpt-4o-mini

    song

    np_max-act-logits · gemini-2.0-flash

    song

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    migrationBuilder
    -0.59
    mybatisplus
    -0.56
    țiilor
    -0.56
    atischen
    -0.47
     doInBackground
    -0.46
    发表于
    -0.44
    iestety
    -0.44
    ]--;
    -0.43
     Necessary
    -0.43
    WebServlet
    -0.42
    POSITIVE LOGITS
    FieldBuilder
    0.62
    bardier
    0.56
     AssemblyCulture
    0.56
    تقاوى
    0.56
    InputBorder
    0.54
    MessageTagHelper
    0.54
    igshid
    0.54
    featureID
    0.54
    OutputType
    0.53
    SharedCtor
    0.52
    Activations Density 5.011%

    No Known Activations