© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 203148
    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_12_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
    ni
    0.39
    sa
    0.38
    D
    0.37
    ONS
    0.33
    еты
    0.31
    V
    0.30
    Diagram
    0.30
    Buildings
    0.30
    eflow
    0.29
    N
    0.29
    POSITIVE LOGITS
    ського
    0.34
     başkan
    0.34
     pericol
    0.31
     бо
    0.30
     escritório
    0.30
    鎚
    0.30
    <0xA1>
    0.30
     avevano
    0.30
     presiden
    0.30
     devrez
    0.29
    Activations Density 0.000%

    No Known Activations