© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 89015
    Prev
    Next
    INDEX
    Explanations

    .

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_60_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
        
    0.67
    ↵↵↵↵
    0.52
    ?...
    0.50
    ...(
    0.48
    at
    0.47
    !...
    0.47
    ...
    0.46
    ...</
    0.46
       
    0.45
    werk
    0.45
    POSITIVE LOGITS
     left
    0.55
     exp
    0.50
     down
    0.49
     error
    0.48
     $*$
    0.48
     errors
    0.47
     ie
    0.46
     ex
    0.45
     subgroups
    0.45
     group
    0.44
    Activations Density 0.016%

    No Known Activations