© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 2864
    Prev
    Next
    INDEX
    Explanations

    words related to legal proceedings and evidence.

    oai_token-act-pair · gemini-2.0-flash

    legal terminology and frameworks

    np_token-act-pair-logits · gpt-4o-mini

    legal claims, evidence

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    ayuno
    -0.48
    gium
    -0.47
    ട്ട
    -0.45
    rasa
    -0.44
    qrstuvwxyz
    -0.44
    cautions
    -0.43
     occhiali
    -0.43
     cease
    -0.42
     purpure
    -0.41
    phal
    -0.41
    POSITIVE LOGITS
    存于互联网档案馆
    0.81
    AxisAlignment
    0.67
    "?>
    0.65
    ScopeManager
    0.63
    adays
    0.59
    RetentionPolicy
    0.57
     useStyles
    0.55
     مشين
    0.55
    脚注の使い方
    0.55
     BorderRadius
    0.54
    Activations Density 3.075%

    No Known Activations