© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 31142
    Prev
    Next
    INDEX
    Explanations

    important to remember

    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_7_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
     attham
    0.82
    𝟭
    0.75
    的时候
    0.73
     bialgebras
    0.73
     υψη
    0.73
    gmzy
    0.73
     atthakath
    0.72
    ១
    0.72
     vutto
    0.71
     vattum
    0.71
    POSITIVE LOGITS
    ة
    1.31
    ↵
    1.18
    ing
    1.09
    ת
    0.99
    ک
    0.97
    us
    0.92
    ر
    0.91
    T
    0.89
    は
    0.88
    N
    0.87
    Activations Density 0.014%

    No Known Activations