© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 93108
    Prev
    Next
    INDEX
    Explanations

    un

    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_60_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
     form
    0.62
    de
    0.60
    t
    0.50
     p
    0.44
     am
    0.44
    form
    0.43
     AL
    0.43
     ag
    0.42
     box
    0.42
     will
    0.42
    POSITIVE LOGITS
    gives
    0.57
    includes
    0.50
    provides
    0.49
     дает
    0.43
    Provides
    0.43
    shows
    0.42
     ز
    0.42
    allows
    0.42
    marshalling
    0.42
    ز
    0.42
    Activations Density 0.000%

    No Known Activations