© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 1925
    Prev
    Next
    INDEX
    Explanations

    absurd

    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_44_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
     Schle
    0.41
     Fiore
    0.38
     schle
    0.37
     Kins
    0.37
    ຽ
    0.33
    ([\
    0.32
     hierarchies
    0.32
    稹
    0.32
     deviates
    0.32
    榇
    0.32
    POSITIVE LOGITS
     ridiculous
    1.29
     absurd
    1.18
     silly
    1.09
     ludicrous
    1.04
     ridicu
    0.98
     absurdity
    0.91
     foolish
    0.82
     absur
    0.79
    posterous
    0.79
     ridiculously
    0.75
    Activations Density 0.158%

    No Known Activations