© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13049
    Prev
    Next
    INDEX
    Explanations

    first person pronouns and associated words that indicate a personal sentiment

    oai_token-act-pair · gemini-2.0-flash

    expressions of love and appreciation

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

    I

    np_max-act-logits · gemini-2.0-flash
    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
    akaian
    -0.69
    __':
    -0.69
     onCreateView
    -0.67
     Himo
    -0.67
    Rhestr
    -0.67
    scalatest
    -0.64
    xodo
    -0.63
    mybatisplus
    -0.63
    ](#
    -0.62
    ]")]
    -0.62
    POSITIVE LOGITS
    Geplaatst
    0.47
     love
    0.46
    ok
    0.43
    AllowUser
    0.42
     pro
    0.41
     Associate
    0.41
     associate
    0.40
    pida
    0.40
     Pro
    0.40
    pro
    0.39
    Activations Density 0.623%

    No Known Activations