© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 134511
    Prev
    Next
    INDEX
    Explanations

    contrasting with comparisons

    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_1_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
    та
    1.29
    ا
    1.21
    ا۔
    1.20
    ।
    1.20
    dır
    1.18
    t
    1.16
    ك
    1.15
    ۔
    1.15
    𝓭
    1.15
    ،
    1.13
    POSITIVE LOGITS
    ado
    1.41
    ized
    1.11
    ️
    0.92
    ↵↵
    0.91
    ido
    0.85
    ulated
    0.84
    amp
    0.84
    ila
    0.83
    u
    0.82
    ien
    0.81
    Activations Density 0.001%

    No Known Activations