© 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. 8777
    Prev
    Next
    INDEX
    Explanations

    how many / what are

    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
    л
    1.01
    त
    0.82
    ν
    0.78
    ar
    0.77
    า
    0.74
    ه
    0.74
    一个
    0.74
    hava
    0.73
    ం
    0.72
    شت
    0.71
    POSITIVE LOGITS
    ется
    0.85
     transom
    0.78
    𝖓
    0.77
    preis
    0.76
     Gründen
    0.73
    resin
    0.70
    髹
    0.69
    nante
    0.69
    чнай
    0.66
    ifiques
    0.65
    Activations Density 0.385%

    No Known Activations