© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 39006
    Prev
    Next
    INDEX
    Explanations

    map

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_57_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
    город
    0.38
     iff
    0.38
    ्त
    0.38
     currentLocation
    0.38
    ӵ
    0.37
     Gagn
    0.37
     lunch
    0.35
    हत
    0.35
    !]
    0.35
     etern
    0.35
    POSITIVE LOGITS
    pe
    0.45
    phans
    0.43
    Lima
    0.40
    pathi
    0.39
    abah
    0.38
    Peru
    0.38
    avacanam
    0.37
    Pe
    0.37
    hanam
    0.37
    ophosph
    0.37
    Activations Density 0.001%

    No Known Activations