© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 112768
    Prev
    Next
    INDEX
    Explanations

    multimodality

    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_2_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
     to
    1.45
     is
    0.94
    '
    0.93
    mie
    0.92
    小
    0.90
    ahme
    0.89
    .
    0.88
     skyrock
    0.87
     was
    0.85
     زبان
    0.85
    POSITIVE LOGITS
    т
    1.53
    る
    1.34
    ת
    1.30
    ING
    1.27
    ın
    1.24
    ib
    1.23
    त
    1.21
    OM
    1.16
    ar
    1.16
    ون
    1.16
    Activations Density 0.000%

    No Known Activations