© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 79462
    Prev
    Next
    INDEX
    Explanations

    you or your

    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_0_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
     can
    1.86
    I
    1.36
    i
    1.34
    ید
    1.33
    는
    1.30
    ي
    1.23
    can
    1.23
    ール
    1.21
    ний
    1.16
    سی
    1.16
    POSITIVE LOGITS
     on
    2.30
    é
    2.00
    The
    1.79
     The
    1.48
    ın
    1.34
    on
    1.34
    os
    1.27
    ’
    1.25
     позволи
    1.22
    ig
    1.21
    Activations Density 0.001%

    No Known Activations