© 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. 8042
    Prev
    Next
    INDEX
    Explanations

    other [Models, Engineering, bulbs, cap, ., side, event, Conditions, systems, luxury]

    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
    ᴜ
    0.82
    ২০
    0.78
    ا
    0.76
    ה
    0.74
    ע
    0.70
     vicenda
    0.69
    েকের
    0.68
    া
    0.67
    serializer
    0.67
     लिए
    0.65
    POSITIVE LOGITS
    am
    0.83
     careful
    0.77
    worldly
    0.77
     nhau
    0.73
     breakpoints
    0.69
     possibilité
    0.67
    ्ठा
    0.67
    ри
    0.67
    થા
    0.66
    éric
    0.66
    Activations Density 0.104%

    No Known Activations