© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 116354
    Prev
    Next
    INDEX
    Explanations

    `False` or `NA` followed by punctuation

    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
    迁移
    0.42
    Transfer
    0.39
    ช่วย
    0.38
    检
    0.38
    移
    0.37
    转移
    0.37
    wiad
    0.37
     влияния
    0.37
    嗖
    0.37
     हस्ता
    0.36
    POSITIVE LOGITS
    sync
    0.38
     shank
    0.38
     Vak
    0.37
     अन्दर
    0.36
     culmin
    0.36
     instead
    0.35
    SYNC
    0.35
     tersebut
    0.35
     invece
    0.35
    instead
    0.35
    Activations Density 0.001%

    No Known Activations