© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 46-GEMMASCOPE-2-TRANSCODER-262K
    4. 204010
    Prev
    Next
    INDEX
    Explanations

    Replit

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    保守
    0.43
     മി
    0.41
    ឪ
    0.38
    民
    0.36
     minuti
    0.36
    queous
    0.36
    建設
    0.36
    玮
    0.36
    webm
    0.35
     snappy
    0.35
    POSITIVE LOGITS
    ыз
    0.44
    ITS
    0.42
    edia
    0.40
    Pointer
    0.38
    IKO
    0.38
    idaire
    0.38
    Serialization
    0.37
    దం
    0.37
    irti
    0.37
    ाइए
    0.36
    Activations Density 0.001%

    No Known Activations