© 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. 134614
    Prev
    Next
    INDEX
    Explanations

    believes

    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
    t
    1.08
    ik
    1.07
     Irland
    1.06
    uk
    1.03
     Italien
    1.02
     It
    1.00
     flexion
    1.00
     Veranst
    1.00
     erinnern
    0.96
    на
    0.95
    POSITIVE LOGITS
    로
    1.19
    으로
    1.17
    ,
    0.93
    ம்
    0.92
    as
    0.89
    วิธี
    0.87
    <0xE0>
    0.85
    時
    0.84
    가
    0.82
    지
    0.80
    Activations Density 0.001%

    No Known Activations