© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 15247
    Prev
    Next
    INDEX
    Explanations

    a mix of question answering and programming-related terms mixed with family history

    oai_token-act-pair · gemini-2.0-flash

    id/ID

    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
     would
    -2.53
    would
    -2.02
    Would
    -1.91
     Would
    -1.91
     WOULD
    -1.56
     zou
    -1.20
     seraient
    -1.16
     sería
    -1.15
     lenne
    -1.14
     zouden
    -1.13
    POSITIVE LOGITS
     id
    0.63
     ID
    0.61
     autorytatywna
    0.56
    getID
    0.54
    TabIndex
    0.52
    Id
    0.51
    ID
    0.51
    RenderAtEndOf
    0.51
     getID
    0.50
     Perché
    0.50
    Activations Density 3.391%

    No Known Activations