© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12555
    Prev
    Next
    INDEX
    Explanations

    language related to legal proceedings, especially judgements and evidence presented to a court and jury

    oai_token-act-pair · gemini-2.0-flash

    Jury, court cases

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    SPJ
    -0.56
    جوايز
    -0.54
    userdetails
    -0.50
     ferons
    -0.49
    QUADS
    -0.48
     smtplib
    -0.48
     jual
    -0.48
     judgement
    -0.48
     Burton
    -0.48
    Redacción
    -0.47
    POSITIVE LOGITS
    HasAnnotation
    0.64
     OFDb
    0.63
    FieldNumber
    0.59
    υγ
    0.56
    MessageOf
    0.53
     กรัม
    0.52
    Personensuche
    0.52
     tiêu
    0.50
    complexType
    0.50
    InvalidProtocol
    0.50
    Activations Density 5.904%

    No Known Activations