© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 12696
    Prev
    Next
    INDEX
    Explanations

    "Tk." and possibly temperatures

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    BufferException
    -0.61
    __*/
    -0.56
    awaiter
    -0.54
    ">//
    -0.53
    MigrationBuilder
    -0.50
    Према
    -0.48
    บุ
    -0.48
    SerializedName
    -0.48
    ciais
    -0.48
     Савезне
    -0.48
    POSITIVE LOGITS
    findpost
    0.61
    mybatisplus
    0.56
    setVerticalGroup
    0.56
     Frisco
    0.53
    envol
    0.51
    Angelina
    0.50
    ip
    0.48
     alugar
    0.48
     ModelExpression
    0.48
    TabIndex
    0.48
    Activations Density 0.992%

    No Known Activations