© 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. 112602
    Prev
    Next
    INDEX
    Explanations

    to send, become, create, start, run

    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
    ме
    1.09
    це
    1.02
    он
    1.02
    𝙚
    0.99
     когато
    0.96
    без
    0.95
    ين
    0.95
    ה
    0.94
    يم
    0.94
    ние
    0.93
    POSITIVE LOGITS
    .
    1.83
    us
    1.65
    to
    1.62
     to
    1.42
    the
    1.34
    ong
    1.30
    ik
    1.25
    om
    1.24
    ag
    1.24
    ?
    1.24
    Activations Density 0.016%

    No Known Activations