© 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-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 8122
    Prev
    Next
    INDEX
    Explanations

    pdf

    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_3_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
    ''_
    1.05
     fumble
    0.95
     рез
    0.95
    Кто
    0.94
     multival
    0.92
     groovy
    0.91
    󠁢
    0.91
    𝓱
    0.91
     nhàng
    0.90
    ית
    0.90
    POSITIVE LOGITS
    ה
    1.31
    a
    0.99
    ja
    0.87
    t
    0.80
    aan
    0.77
    erd
    0.77
    ्ड
    0.76
    ոլ
    0.74
    اتف
    0.73
    aia
    0.71
    Activations Density 0.001%

    No Known Activations