© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 58429
    Prev
    Next
    INDEX
    Explanations

    tokens ending in ash, ast, ass, osh

    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_2_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
    2
    1.37
    ل
    1.17
    s
    1.16
    ra
    1.09
    with
    1.06
    ל
    1.05
    つ
    1.01
    ian
    1.00
    our
    0.99
    لیس
    0.98
    POSITIVE LOGITS
    ৬
    1.14
    ко
    1.12
    в
    1.10
    হ
    1.09
    ти
    0.98
    ্কার
    0.98
    is
    0.98
    W
    0.96
     onstage
    0.93
    都知道
    0.92
    Activations Density 0.001%

    No Known Activations