© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 119240
    Prev
    Next
    INDEX
    Explanations

    is generally, is quite, is speculated

    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_27_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
     muere
    0.34
    ಲ್ಯ
    0.29
    出発
    0.29
    业务
    0.29
     ఉంది
    0.29
     المخت
    0.29
     activa
    0.28
     악
    0.28
     예정
    0.28
     бре
    0.27
    POSITIVE LOGITS
     prestig
    0.32
    az
    0.32
    so
    0.31
    Compass
    0.31
    Gall
    0.31
    ost
    0.31
    important
    0.30
    such
    0.30
    wang
    0.29
    now
    0.29
    Activations Density 0.008%

    No Known Activations