© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 168948
    Prev
    Next
    INDEX
    Explanations

    client

    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_56_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
    เห็น
    0.42
    ❔
    0.42
    !!!!!!!!
    0.41
    !!!!!
    0.41
    hood
    0.40
    ‼
    0.40
    !!!!!!!
    0.39
     \"
    0.38
    !!!!!!!!!!!!!!!!
    0.38
    ‼️
    0.38
    POSITIVE LOGITS
     clearest
    0.37
     ወደ
    0.36
     Dread
    0.36
     dread
    0.36
     tough
    0.35
     thin
    0.35
     Input
    0.35
    thin
    0.35
     egos
    0.35
     getInput
    0.35
    Activations Density 0.001%

    No Known Activations