© 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. 90919
    Prev
    Next
    INDEX
    Explanations

    protocols, virtual interfaces, and names

    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
    h
    1.23
    k
    0.94
    p
    0.74
    v
    0.67
    c
    0.66
     in
    0.62
    al
    0.62
    hase
    0.60
    w
    0.58
    t
    0.57
    POSITIVE LOGITS
    ਰ
    0.65
    のは
    0.63
    ર
    0.61
    ר
    0.61
    お店
    0.60
    使用
    0.59
    पहर
    0.59
     flaming
    0.58
     proviso
    0.58
     pungent
    0.58
    Activations Density 0.021%

    No Known Activations