© 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. 88079
    Prev
    Next
    INDEX
    Explanations

    -

    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
    s
    0.72
    efeuille
    0.56
    its
    0.54
    problem
    0.53
    ford
    0.52
    scape
    0.50
    land
    0.50
    song
    0.49
    sburg
    0.49
    ی
    0.48
    POSITIVE LOGITS
    "
    0.63
    ”
    0.53
     ac
    0.52
    ATIVE
    0.49
    "/
    0.47
    ACM
    0.47
    "/"
    0.46
    AC
    0.44
    ADB
    0.44
     bree
    0.44
    Activations Density 0.002%

    No Known Activations