© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 62127
    Prev
    Next
    INDEX
    Explanations

    negative concepts

    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_59_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
     -
    0.68
     ([
    0.50
     (_
    0.48
     (:
    0.48
     *(
    0.46
     _
    0.45
     (*
    0.41
     [`
    0.41
     (=
    0.41
    }([
    0.41
    POSITIVE LOGITS
    NEGATIVE
    0.62
     NEG
    0.62
     отрица
    0.61
    負
    0.59
     Negative
    0.57
     nég
    0.56
     negatively
    0.55
    Negative
    0.55
     neg
    0.55
     negative
    0.55
    Activations Density 0.001%

    No Known Activations