© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-4B-IT
    3. 5-GEMMASCOPE-2-TRANSCODER-262K
    4. 3204
    Prev
    Next
    INDEX
    Explanations

    code comments and programming structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_5_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cans
    2.43
    h
    2.41
    g
    2.21
    ዖ
    2.20
    dress
    2.07
    c
    2.03
    𝐠
    2.01
    𝙥
    2.01
     기타
    2.01
    cima
    1.97
    POSITIVE LOGITS
     boldness
    2.03
     siento
    1.92
     psychedelic
    1.86
    (('
    1.85
     afgelopen
    1.82
     fleste
    1.81
    }">
    1.79
    ้
    1.79
    его
    1.79
    ۣ
    1.78
    Activations Density 0.077%

    No Known Activations