© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 181970
    Prev
    Next
    INDEX
    Explanations

    Python package metadata

    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_29_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
    戶
    0.38
     Picker
    0.36
    FL
    0.36
     RESOURCE
    0.36
    GL
    0.35
     Reasoning
    0.35
    工
    0.35
     computed
    0.35
     MSP
    0.34
    众
    0.34
    POSITIVE LOGITS
     botched
    0.46
     exile
    0.43
    역시
    0.42
     desember
    0.42
     sAlarm
    0.41
     bodyguard
    0.41
     instalment
    0.40
    damn
    0.40
    óri
    0.39
     december
    0.39
    Activations Density 0.000%

    No Known Activations