© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 204554
    Prev
    Next
    INDEX
    Explanations

    Lithium-Ion, DOS, GlaDOS

    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
     ofer
    1.30
     as
    1.23
    ,
    1.09
    </h3>
    1.07
     воен
    1.04
     to
    1.01
    ك
    1.01
    EL
    1.00
     ולה
    1.00
     популяр
    0.98
    POSITIVE LOGITS
    ad
    1.26
    ни
    1.20
    ون
    1.16
    <0xA1>
    1.10
    ate
    1.08
    ва
    1.06
    ina
    1.05
    ра
    1.04
    ρα
    1.03
    (
    1.02
    Activations Density 0.000%

    No Known Activations