© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 206770
    Prev
    Next
    INDEX
    Explanations

    indie game development

    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_10_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
     an
    0.66
     biscuit
    0.65
    ک
    0.64
     ",
    0.63
     point
    0.61
     form
    0.60
     ouverte
    0.60
     chimney
    0.59
     one
    0.59
     pads
    0.58
    POSITIVE LOGITS
    ৬
    0.65
    ১০
    0.60
    ७
    0.56
    Studies
    0.55
    кина
    0.53
    արգ
    0.53
    Because
    0.53
     因为
    0.53
    ផ
    0.53
    ৭
    0.52
    Activations Density 0.011%

    No Known Activations