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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 8-GEMMASCOPE-TRANSCODER-16K
    4. 1244
    Prev
    Next
    INDEX
    Explanations

    numerical data, especially percentages, table tags and floating point numbers

    oai_token-act-pair · gemini-2.0-flash

    td

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     RSSSF
    -0.65
    ூர்
    -0.60
    RenderAtEndOf
    -0.59
     Parcelable
    -0.58
     Exactos
    -0.55
    ReusableCell
    -0.55
     EconPapers
    -0.52
    ^(@)
    -0.52
    ]-->
    -0.51
    okovic
    -0.51
    POSITIVE LOGITS
    ImageContext
    0.47
    WebElementEntity
    0.45
    remont
    0.42
    нрави
    0.41
    ISupport
    0.40
     diber
    0.40
    :+:
    0.40
    Occurred
    0.40
     createStore
    0.40
    kloped
    0.40
    Activations Density 1.740%

    No Known Activations