© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 28462
    Prev
    Next
    INDEX
    Explanations

    strength and emphasis

    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_40_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
     personal
    0.41
     brightness
    0.38
    ⁷
    0.36
     kiş
    0.36
     osob
    0.35
     done
    0.35
     SDLK
    0.35
    эс
    0.35
    pyrazin
    0.35
     ots
    0.35
    POSITIVE LOGITS
    Strong
    0.92
    strong
    0.89
     Strong
    0.82
    強
    0.80
     strong
    0.79
    强
    0.79
     fuertes
    0.77
     fuerte
    0.74
     fortes
    0.73
     Strongly
    0.71
    Activations Density 0.025%

    No Known Activations