© 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. 142197
    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
    탈
    0.51
    mig
    0.50
    정
    0.50
    izações
    0.49
    Degrees
    0.49
    בי
    0.47
    લી
    0.47
    Defer
    0.47
    〃
    0.47
    Έ
    0.47
    POSITIVE LOGITS
     (
    0.50
     championed
    0.47
     собой
    0.46
     chieft
    0.46
     chieftain
    0.46
     disruption
    0.45
     disturbing
    0.45
     ৩৬
    0.45
     dynamite
    0.43
    aien
    0.43
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.