© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 13567
    Prev
    Next
    INDEX
    Explanations

    c++ code blocks

    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_15_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
    ят
    0.29
     avaient
    0.27
    ም
    0.25
    㷌
    0.24
    ໄປ
    0.23
    ೆ
    0.23
     seguintes
    0.23
     desej
    0.23
    >$
    0.22
     вода
    0.22
    POSITIVE LOGITS
     Force
    0.24
     Control
    0.23
     Tipo
    0.23
     און
    0.23
    Force
    0.23
    infra
    0.23
     Implementation
    0.22
     Number
    0.22
    overy
    0.22
     Version
    0.22
    Activations Density 0.011%

    No Known Activations