© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 10779
    Prev
    Next
    INDEX
    Explanations

    the words "must," "can," "should," "morate", and "que"

    oai_token-act-pair · gemini-2.0-flash

    ust

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    HomeAsUpEnabled
    -0.61
     Ours
    -0.59
    ázaro
    -0.59
    WHEREAS
    -0.55
    Ours
    -0.55
     Witkin
    -0.53
     InputDecoration
    -0.52
    UserScript
    -0.52
    Herzliche
    -0.52
     getItemCount
    -0.52
    POSITIVE LOGITS
    <bos>
    1.48
     must
    0.71
    must
    0.60
     Must
    0.57
    Must
    0.56
    MigrationBuilder
    0.56
    Билгалдахарш
    0.54
    要有
    0.54
     måste
    0.51
     nakalista
    0.48
    Activations Density 1.643%

    No Known Activations