© 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. 242579
    Prev
    Next
    INDEX
    Explanations

    words like strong and weak

    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
     strong
    1.73
     strongly
    1.69
    Strong
    1.68
    strong
    1.59
     STRONG
    1.56
     Strong
    1.55
    强
    1.51
     Strongly
    1.49
    強
    1.46
    STRONG
    1.45
    POSITIVE LOGITS
    CIAL
    0.41
     cookie
    0.36
     authorized
    0.35
     چاندی
    0.35
     ሴ
    0.35
     Rockies
    0.35
     Andersen
    0.34
    篒
    0.34
     Shadow
    0.34
    )}(\
    0.34
    Activations Density 0.034%

    No Known Activations