© 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. 39075
    Prev
    Next
    INDEX
    Explanations

    smiley face

    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
     ERROR
    0.32
     (*
    0.29
     FINANCIAL
    0.27
    cled
    0.27
     Vors
    0.27
     contenedor
    0.27
     Results
    0.27
     RESULTS
    0.26
     زیادہ
    0.25
    werpen
    0.25
    POSITIVE LOGITS
    ),\
    0.25
    Abroad
    0.25
    ⅓
    0.24
    并在
    0.24
     වලින්
    0.24
    \\.
    0.24
    रहे
    0.24
    và
    0.23
    Cabinet
    0.23
    ᱾
    0.23
    Activations Density 0.027%

    No Known Activations