© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 12309
    Prev
    Next
    INDEX
    Explanations

    haunted by

    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
    ants
    0.44
    TREE
    0.43
     Expanding
    0.42
     সতীশ
    0.42
    izieren
    0.42
    ដោយ
    0.42
     Lazy
    0.41
    汆
    0.40
     Bedeutung
    0.40
     laziness
    0.40
    POSITIVE LOGITS
    v
    0.50
    nBitCount
    0.45
    での
    0.44
     questa
    0.44
     già
    0.43
     partita
    0.43
     فری
    0.42
    ной
    0.42
    न
    0.42
     ल
    0.42
    Activations Density 0.038%

    No Known Activations