© 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. 3138
    Prev
    Next
    INDEX
    Explanations

    words often used in legal reports and news articles about crime.

    oai_token-act-pair · gemini-2.0-flash

    words related to verdicts and judgments

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

    Validity, correctness

    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
    MigrationBuilder
    -0.66
     frequenza
    -0.57
    VersionUID
    -0.57
     empê
    -0.57
     kerül
    -0.56
     consigned
    -0.52
     ricev
    -0.52
     empêche
    -0.51
     fatica
    -0.51
     asegu
    -0.49
    POSITIVE LOGITS
     correct
    1.24
     valid
    1.03
     wrong
    1.02
    correct
    0.99
    Correct
    0.88
     Correct
    0.86
     good
    0.85
    valid
    0.83
     true
    0.81
    wrong
    0.81
    Activations Density 4.568%

    No Known Activations