© 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
    3. Gemma-3-27B-IT
    5. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 196867
    Prev
    Next
    INDEX
    Explanations

    scientific or technical context

    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_9_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
     branching
    0.52
     branched
    0.52
     creek
    0.50
     w
    0.49
     statement
    0.47
     index
    0.46
     branch
    0.46
     crowd
    0.46
     values
    0.45
     circular
    0.45
    POSITIVE LOGITS
    Serbia
    0.56
    aunque
    0.52
    ElementType
    0.52
    ቝ
    0.50
    Terror
    0.49
    Borrow
    0.48
    Stable
    0.48
    pèce
    0.47
    Accuracy
    0.47
     Ба
    0.47
    Activations Density 0.000%

    No Known Activations