© 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. 18916
    Prev
    Next
    INDEX
    Explanations

    walking

    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
    କ
    0.31
    <0x80>
    0.31
     आणि
    0.30
     miatt
    0.30
     ou
    0.30
     Bonnet
    0.30
    issage
    0.29
     операция
    0.29
    agis
    0.29
    ichier
    0.29
    POSITIVE LOGITS
     这里
    0.30
    Ironically
    0.29
    贰
    0.29
    疗
    0.29
    Vanilla
    0.28
     utilidad
    0.28
     以下
    0.28
    Tenemos
    0.28
    Aside
    0.27
    Therm
    0.27
    Activations Density 0.008%

    No Known Activations