© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 11857
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with possibility or ability

    oai_token-act-pair · gemini-2.0-flash

    say "to" or "of"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     verder
    -0.19
     láser
    -0.17
     septem
    -0.17
     vertes
    -0.16
     Etats
    -0.16
     sze
    -0.15
     drenaje
    -0.15
     skola
    -0.15
     oxígeno
    -0.15
     ugy
    -0.15
    POSITIVE LOGITS
     مشين
    1.00
    StoryboardSegue
    0.95
     snippetHide
    0.82
    ReusableCell
    0.82
    GraphicsUnit
    0.82
    queryInterface
    0.81
    帖最后由
    0.81
    __))
    0.81
    MigrationBuilder
    0.79
     Савезне
    0.79
    Activations Density 14.558%

    No Known Activations