© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 15601
    Prev
    Next
    INDEX
    Explanations

    first person verbs about thinking and desiring

    oai_token-act-pair · gemini-2.0-flash

    desire or intent

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    gameserver
    -0.52
    }}$\\
    -0.52
     }}</
    -0.52
     bidra
    -0.52
     ''),
    -0.50
     }}^{\
    -0.50
    }");
    -0.49
    %;">
    -0.49
     ""),
    -0.48
    `{.
    -0.47
    POSITIVE LOGITS
    ScopeManager
    0.82
    TintMode
    0.74
    migrationBuilder
    0.73
    InputBorder
    0.71
     незавершена
    0.67
     виправивши
    0.66
    LOYEES
    0.65
    apunov
    0.65
    UserScript
    0.63
    SourceChecksum
    0.62
    Activations Density 0.280%

    No Known Activations