© 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. 8237
    Prev
    Next
    INDEX
    Explanations

    model addressing you

    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
    ه
    2.24
    ться
    2.24
    に
    2.17
     дочь
    1.98
     asa
    1.96
    у
    1.95
    ء
    1.93
     все
    1.91
    uded
    1.90
     खासा
    1.89
    POSITIVE LOGITS
     ĝi
    2.38
    WARNING
    2.35
    តែ
    2.35
    ियों
    2.31
    tener
    2.31
    Zap
    2.30
    mäß
    2.26
    apparent
    2.25
    nitrogen
    2.24
    ت
    2.23
    Activations Density 0.016%

    No Known Activations