© 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. 157621
    Prev
    Next
    INDEX
    Explanations

    Sauerbraten, brötchen, Brand, Bratislava

    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
    0
    1.41
    P
    1.37
    J
    1.29
    H
    1.23
    GR
    1.21
    OR
    1.20
    W
    1.20
    S
    1.19
    you
    1.18
    TS
    1.17
    POSITIVE LOGITS
     is
    1.30
    ر
    1.20
     intellig
    1.05
    ä
    1.02
    ن
    1.02
     and
    1.00
    Ӣ
    0.97
     accusation
    0.94
    ي
    0.94
     individualized
    0.93
    Activations Density 0.000%

    No Known Activations