© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 239514
    Prev
    Next
    INDEX
    Explanations

    forms or types

    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_25_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
     detalhes
    0.32
     Olha
    0.30
     folgte
    0.30
     détails
    0.30
    CASCADE
    0.30
    GCG
    0.30
     uguale
    0.30
    ഞ
    0.29
     ENGINE
    0.29
     BUFFER
    0.29
    POSITIVE LOGITS
     carries
    0.28
    www
    0.28
    owan
    0.27
    র্কের
    0.27
     truly
    0.26
    ffiti
    0.26
     reputation
    0.25
    otine
    0.25
     televised
    0.25
     snapping
    0.25
    Activations Density 0.023%

    No Known Activations