© 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. 8186
    Prev
    Next
    INDEX
    Explanations

    custom, build, make, check, highlight, insert, hash, fade

    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
    on
    2.27
    oretical
    2.24
    ју
    2.06
     }}$.
    1.87
    ㎿
    1.80
    unu
    1.79
    тип
    1.77
    onat
    1.77
    ्हान
    1.76
    ae
    1.73
    POSITIVE LOGITS
    ি
    2.15
    ु
    2.01
    কে
    1.95
    dd
    1.89
    ন
    1.87
    ے
    1.86
     hyperplasia
    1.85
    pregn
    1.85
    ка
    1.85
    to
    1.83
    Activations Density 0.010%

    No Known Activations