© 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-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 42143
    Prev
    Next
    INDEX
    Explanations

    free and easy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-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
    -
    1.11
    و
    0.68
    el
    0.67
    ต์
    0.63
    fection
    0.63
     gimnas
    0.59
     harapan
    0.59
    -{\
    0.58
    -$\
    0.58
     tramp
    0.57
    POSITIVE LOGITS
    t
    1.27
    د
    0.82
    ত
    0.74
    ت
    0.71
    ER
    0.70
    ts
    0.70
    tx
    0.69
    ר
    0.66
    tl
    0.65
    tte
    0.64
    Activations Density 0.002%

    No Known Activations