© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12125
    Prev
    Next
    INDEX
    Explanations

    clauses suggesting legal or factual insufficiency

    oai_token-act-pair · gemini-2.0-flash

    legal arguments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     Administrativna
    -0.73
    PreferredItem
    -0.65
     atleast
    -0.60
     Baillargeon
    -0.60
     <",
    -0.60
     itſelf
    -0.59
     mindestens
    -0.59
    getChildAt
    -0.59
    InMillis
    -0.58
     vielmehr
    -0.57
    POSITIVE LOGITS
    ↵
    0.52
    ftagPool
    0.47
     or
    0.47
    /******/
    0.46
    .
    0.45
    DataContract
    0.44
     Вікі
    0.43
    <bos>
    0.42
     aggi
    0.42
     me
    0.42
    Activations Density 2.714%

    No Known Activations