© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 242231
    Prev
    Next
    INDEX
    Explanations

    app =

    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_40_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
    Gregory
    0.42
    app
    0.42
    GAMMA
    0.41
     Gregory
    0.39
    Connor
    0.39
    Icon
    0.38
    忽
    0.37
    osil
    0.37
    慶
    0.36
    expr
    0.36
    POSITIVE LOGITS
     producción
    0.39
    amins
    0.37
     vaginalis
    0.37
    阱
    0.37
     handlerInput
    0.36
     itinerant
    0.36
     Produktion
    0.35
     bain
    0.35
    वासन
    0.35
    impose
    0.35
    Activations Density 0.000%

    No Known Activations