© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 200263
    Prev
    Next
    INDEX
    Explanations

    negated statements

    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_12_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
    ing
    0.80
    RL
    0.60
    Res
    0.59
    equal
    0.59
    Ms
    0.59
    ة
    0.58
    als
    0.57
    DataFrame
    0.55
    Map
    0.54
    Basic
    0.54
    POSITIVE LOGITS
     posits
    0.68
     exploits
    0.67
    ي
    0.64
     argued
    0.63
     incentiv
    0.63
     artigos
    0.61
    ו
    0.61
     outputs
    0.61
     sociais
    0.61
     contrasts
    0.59
    Activations Density 0.000%

    No Known Activations