© 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. 126620
    Prev
    Next
    INDEX
    Explanations

    names with "ill" or "ion" or "avenue" or "street"

    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
    ной
    0.69
     disapproval
    0.66
     troubleshoot
    0.65
    ﺎ
    0.60
     démontré
    0.60
     burgeoning
    0.59
    എ
    0.59
     glamorous
    0.59
     documenti
    0.59
     deliberately
    0.58
    POSITIVE LOGITS
    ت
    0.88
    h
    0.68
    fts
    0.67
    تون
    0.66
    衽
    0.66
    変更
    0.65
    ferm
    0.64
    phthal
    0.64
     Phan
    0.63
    its
    0.63
    Activations Density 0.000%

    No Known Activations