© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 86581
    Prev
    Next
    INDEX
    Explanations

    foreplay

    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_3_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
    are
    0.71
    as
    0.70
     foreshadow
    0.67
    мента
    0.66
    kenalkan
    0.66
     insuring
    0.65
    ки
    0.62
    դ
    0.62
    льна
    0.62
    of
    0.61
    POSITIVE LOGITS
    ("
    0.75
    I
    0.74
     accolades
    0.73
    Failed
    0.64
    حياته
    0.63
    January
    0.61
     u
    0.60
     odlič
    0.60
     život
    0.59
    Petition
    0.59
    Activations Density 0.000%

    No Known Activations