© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 78705
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_0_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
     (
    0.63
    0.59
    0
    0.58
    MST
    0.45
    #
    0.45
    with
    0.44
    _
    0.44
     inform
    0.44
     visited
    0.43
    ET
    0.43
    POSITIVE LOGITS
    ൻ
    0.66
    तोड़
    0.64
    ಊ
    0.64
    abhavena
    0.61
    𝗔
    0.60
    erreur
    0.60
    йдз
    0.60
     завдання
    0.59
     ಪೂರ್ವ
    0.59
    ദി
    0.57
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.