© 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. 107486
    Prev
    Next
    INDEX
    Explanations

    Doris and Boris

    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
    1.46
    ET
    1.14
     for
    1.12
    d
    1.12
    EN
    1.11
    もら
    1.11
    У
    1.09
    К
    1.08
     baits
    1.06
    Α
    1.06
    POSITIVE LOGITS
    ik
    1.33
    ä
    1.23
    ков
    1.08
    yd
    1.04
    ק
    1.03
    си
    1.02
    im
    1.00
    ोन
    0.98
    ти
    0.97
    ip
    0.97
    Activations Density 0.000%

    No Known Activations