© 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. 79540
    Prev
    Next
    INDEX
    Explanations

    neutrality

    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
    م
    1.65
     in
    1.38
    па
    1.28
    не
    1.27
    ب
    1.25
    s
    1.23
    na
    1.23
     estern
    1.14
    হ
    1.13
     an
    1.12
    POSITIVE LOGITS
    -
    1.95
    i
    1.65
    ol
    1.40
    થી
    1.38
    al
    1.37
    ://
    1.36
    el
    1.35
    2
    1.34
    ’
    1.31
    は
    1.30
    Activations Density 0.000%

    No Known Activations