© 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. 11082
    Prev
    Next
    INDEX
    Explanations

    CRC errors

    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
    ,
    0.14
    '
    0.14
     Ne
    0.13
     poch
    0.13
    !
    0.13
    ?
    0.13
     Brand
    0.12
     first
    0.12
    ني
    0.12
     creando
    0.12
    POSITIVE LOGITS
     ಬಹು
    0.14
     riun
    0.14
     μέσω
    0.14
    eneuve
    0.13
    瀋
    0.13
    SIZ
    0.13
     avaliar
    0.13
    服務
    0.13
     famílias
    0.13
    Οι
    0.13
    Activations Density 0.007%

    No Known Activations