© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 3990
    Prev
    Next
    INDEX
    Explanations

    mentions of accolades, achievements, and recognition

    oai_token-act-pair · gemini-2.0-flash

    award

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     award
    -2.39
     Award
    -2.23
     awards
    -2.16
    Award
    -2.09
     Awards
    -2.00
     AWARD
    -1.91
    award
    -1.89
    Awards
    -1.88
    awards
    -1.80
     AWARDS
    -1.70
    POSITIVE LOGITS
    ParallelGroup
    0.85
     الرياضيه
    0.73
    MigrationBuilder
    0.72
     Roskov
    0.67
    ScopeManager
    0.67
    RectangleBorder
    0.63
     cref
    0.63
    DebuggerNonUser
    0.63
     endforeach
    0.61
    SourceChecksum
    0.60
    Activations Density 7.341%

    No Known Activations