© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 20090
    Prev
    Next
    INDEX
    Explanations

    very

    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_56_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
    ×
    0.76
     ×
    0.73
     Ã
    0.66
     Â
    0.57
    Ã
    0.57
    
    0.55
     Ă
    0.45
    £
    0.45
     £
    0.45
    ⊗
    0.42
    POSITIVE LOGITS
     ver
    1.53
     Ver
    1.47
    Ver
    1.39
    ver
    1.17
    VER
    1.00
     VER
    0.95
     muy
    0.76
     veril
    0.74
     too
    0.72
    very
    0.72
    Activations Density 0.052%

    No Known Activations