© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 232545
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_6_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
    ituus
    0.77
    baar
    0.70
    ۳
    0.69
    ții
    0.69
    ży
    0.67
    ۰
    0.67
    łow
    0.66
    ۰۰
    0.66
    ivă
    0.65
    ės
    0.64
    POSITIVE LOGITS
    n
    1.66
    t
    1.49
    w
    1.43
    y
    1.38
    x
    1.35
    r
    1.34
    on
    1.31
    p
    1.28
    an
    1.22
    i
    1.20
    Activations Density 0.000%

    No Known Activations