© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 194212
    Prev
    Next
    INDEX
    Explanations

    worldwide

    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_4_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
    ’
    1.16
    #
    0.95
    (
    0.86
    esse
    0.86
    س
    0.84
    nın
    0.80
    edi
    0.80
    م
    0.80
    V
    0.78
    ’.
    0.77
    POSITIVE LOGITS
    е
    1.40
    ри
    1.17
    ра
    1.13
    те
    1.13
    ло
    1.02
    ре
    1.01
    il
    0.96
     will
    0.96
    ૦
    0.90
    п
    0.89
    Activations Density 0.026%

    No Known Activations