© 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. 232132
    Prev
    Next
    INDEX
    Explanations

    derivative of

    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_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
    رک
    0.98
    𝗱
    0.89
    ب
    0.87
    𝗳
    0.86
    이미
    0.84
    慜
    0.82
    ل
    0.82
    乆
    0.82
    ロッパ
    0.80
    a
    0.80
    POSITIVE LOGITS
    ag
    0.95
    ado
    0.91
    U
    0.88
    0.88
    ية
    0.87
    ings
    0.86
    ice
    0.79
    schw
    0.79
    t
    0.79
    es
    0.78
    Activations Density 0.001%

    No Known Activations