© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 162930
    Prev
    Next
    INDEX
    Explanations

    allows/gives time

    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_31_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
     стандарта
    0.33
    ologija
    0.32
     grips
    0.31
    })-
    0.31
     zů
    0.31
     Remain
    0.30
    hota
    0.30
    TableHeader
    0.30
    )\$(
    0.30
    utet
    0.30
    POSITIVE LOGITS
     time
    0.36
     digested
    0.36
     drained
    0.35
     timed
    0.35
     время
    0.34
     completed
    0.33
    time
    0.32
    ื่อย
    0.32
    ahili
    0.32
    Dod
    0.31
    Activations Density 0.002%

    No Known Activations