© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11946
    Prev
    Next
    INDEX
    Explanations

    punctuation and formatting related to academic publications

    oai_token-act-pair · gemini-2.0-flash

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     HasFactory
    -0.67
    endphp
    -0.53
     Infórmanos
    -0.47
    Set
    -0.45
    انو
    -0.44
    ?>
    -0.43
    DJANGO
    -0.42
    ########.
    -0.42
     interesa
    -0.42
     صوتيه
    -0.42
    POSITIVE LOGITS
     Paglinawan
    0.72
    versiti
    0.60
    getSystemService
    0.60
    
    0.58
    endwhile
    0.57
     Roskov
    0.54
    Portail
    0.54
    RuleContext
    0.53
    CloseOperation
    0.52
    исленность
    0.52
    Activations Density 1.176%

    No Known Activations