© 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. 107836
    Prev
    Next
    INDEX
    Explanations

    possibly followed by action/state

    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
    n
    1.61
    m
    1.51
    j
    1.47
    t
    1.37
    y
    1.37
    리
    1.34
    de
    1.34
    re
    1.29
    (
    1.24
    w
    1.22
    POSITIVE LOGITS
     occasioned
    1.08
    ﺗ
    1.04
     atteint
    1.02
     vezes
    1.02
     раду
    1.00
     allgemeinen
    1.00
     יל
    1.00
     сорти
    0.99
     зависи
    0.98
     були
    0.97
    Activations Density 0.000%

    No Known Activations