© 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. 34258
    Prev
    Next
    INDEX
    Explanations

    city-state

    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
     can
    0.47
    ২০
    0.45
     غير
    0.44
    ጬ
    0.43
     regalo
    0.41
     queso
    0.40
     не
    0.40
     לא
    0.40
    <unused1024>
    0.40
    <unused512>
    0.39
    POSITIVE LOGITS
    '
    0.59
    1
    0.57
    a
    0.50
    f
    0.47
    u
    0.42
    st
    0.42
    k
    0.41
    b
    0.38
    h
    0.38
    the
    0.37
    Activations Density 0.002%

    No Known Activations