© 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. 201739
    Prev
    Next
    INDEX
    Explanations

    metal, bounty, Japan, restore

    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
    as
    1.27
    다
    1.18
    да
    1.12
    en
    1.08
    ാർ
    1.02
    s
    1.02
    in
    1.01
    are
    1.00
    sı
    1.00
    ни
    0.98
    POSITIVE LOGITS
    1.31
    '
    1.05
    -
    1.02
    .
    0.98
    &#
    0.76
     triangulation
    0.74
     acuity
    0.70
     cupboards
    0.69
    â
    0.69
    *
    0.69
    Activations Density 0.000%

    No Known Activations