© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 3341
    Prev
    Next
    INDEX
    Explanations

    words related to accusations, blame, and the legal system

    oai_token-act-pair · gemini-2.0-flash

    against/blame

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    Bry
    -0.45
    TableModel
    -0.43
    dal
    -0.42
    Var
    -0.41
     Bry
    -0.41
    iseite
    -0.40
     Ser
    -0.40
     ser
    -0.40
    ported
    -0.39
    ModelAdmin
    -0.39
    POSITIVE LOGITS
     against
    1.07
    against
    1.04
     blaming
    0.92
     targeting
    0.91
     Against
    0.90
    Against
    0.89
     Targeting
    0.88
     accus
    0.87
     blamed
    0.86
     indict
    0.86
    Activations Density 2.823%

    No Known Activations