© 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. 4615
    Prev
    Next
    INDEX
    Explanations

    the word "main" within code snippets

    oai_token-act-pair · gemini-2.0-flash

    main

    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
     Efq
    -0.81
     snippetHide
    -0.71
    }]
    -0.64
     nakalista
    -0.64
     Majefty
    -0.63
     Jefus
    -0.60
     occaf
    -0.60
    '])
    -0.59
    };*/
    -0.58
     giudi
    -0.58
    POSITIVE LOGITS
     wireType
    0.82
    RenderAtEndOf
    0.67
    olol
    0.63
     costas
    0.56
     оригіналу
    0.54
    TRAILING
    0.54
     manos
    0.53
    rouvez
    0.52
     ProtoMessage
    0.52
    APORE
    0.50
    Activations Density 0.343%

    No Known Activations