© 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. 39187
    Prev
    Next
    INDEX
    Explanations

    would like to request

    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
    ي
    0.93
    로
    0.87
    ו
    0.75
    ب
    0.73
    <0x80>
    0.72
    3
    0.72
    は
    0.69
    는
    0.68
    м
    0.67
    ция
    0.65
    POSITIVE LOGITS
     Trouble
    0.74
    an
    0.66
     it
    0.65
     analyze
    0.64
     an
    0.61
     access
    0.60
    ig
    0.59
     Access
    0.59
     Clipper
    0.59
    st
    0.58
    Activations Density 0.042%

    No Known Activations