© 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. 205167
    Prev
    Next
    INDEX
    Explanations

    say yes

    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
     É
    1.70
    É
    1.56
     È
    1.30
     é
    1.28
     Ã
    1.26
    è
    1.23
    é
    1.21
    È
    1.15
     ê
    1.05
     ē
    1.02
    POSITIVE LOGITS
    ricting
    0.43
     byd
    0.42
    irti
    0.39
    ictwa
    0.39
    Es
    0.39
    །
    0.38
    itaj
    0.38
    ፍት
    0.37
    াযোগ
    0.37
    ftar
    0.35
    Activations Density 0.002%

    No Known Activations