© 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. 92305
    Prev
    Next
    INDEX
    Explanations

    Art and culture

    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
    Ab
    0.74
    Aqu
    0.68
    Add
    0.65
    Anna
    0.64
    Am
    0.62
    '
    0.61
    Antonio
    0.59
    Er
    0.59
    Ana
    0.59
    Ar
    0.58
    POSITIVE LOGITS
     se
    0.42
     RK
    0.41
     rit
    0.39
     Cor
    0.38
     minority
    0.37
     pièce
    0.37
     භ
    0.37
     Tekh
    0.36
     Vec
    0.36
     intéress
    0.36
    Activations Density 0.005%

    No Known Activations