© 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. 205163
    Prev
    Next
    INDEX
    Explanations

    cerebro

    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
    ;
    1.49
    ).
    1.03
     habil
    1.00
    _
    0.99
    >
    0.93
    4
    0.92
     Τ
    0.92
     mering
    0.90
     Վ
    0.89
    ড
    0.88
    POSITIVE LOGITS
    ны
    1.19
    бо
    1.14
    да
    1.13
    к
    1.11
     on
    1.07
    as
    1.06
    л
    1.04
    بي
    1.02
    ası
    1.01
    ма
    1.00
    Activations Density 0.001%

    No Known Activations