© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 43800
    Prev
    Next
    INDEX
    Explanations

    sounds cheesy, Instant bonding, right here

    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_13_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
    вший
    0.52
     ચંદ્ર
    0.47
     активность
    0.46
    螅
    0.46
    Э
    0.46
    нан
    0.45
    Referencias
    0.45
    unavailable
    0.45
    Mario
    0.44
    魍
    0.44
    POSITIVE LOGITS
     likeness
    0.46
     .
    0.43
     e
    0.43
     profiles
    0.42
    _
    0.42
     hypertensive
    0.41
     trousers
    0.41
     pr
    0.40
     g
    0.39
     folders
    0.38
    Activations Density 0.127%

    No Known Activations