© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 151166
    Prev
    Next
    INDEX
    Explanations

    random, varying, velocities, specialty

    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_18_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
     את
    0.50
     élarg
    0.47
     המח
    0.46
    ক
    0.46
    BadRequest
    0.45
     αρκε
    0.45
    Missense
    0.44
    偻
    0.43
    มีความ
    0.43
     alat
    0.43
    POSITIVE LOGITS
    köz
    0.46
    kol
    0.46
    gate
    0.46
    bol
    0.45
    ly
    0.44
    opes
    0.44
    ቴ
    0.44
    licas
    0.42
    inator
    0.42
    ighters
    0.42
    Activations Density 0.000%

    No Known Activations