© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 45356
    Prev
    Next
    INDEX
    Explanations

    proof by contradiction

    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_22_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
     (&
    0.27
     Sampson
    0.26
    verbs
    0.25
     BUT
    0.24
     agrav
    0.23
     buona
    0.23
     reflexes
    0.23
     penulis
    0.23
     soluciones
    0.23
     Reflex
    0.23
    POSITIVE LOGITS
     JCB
    0.28
     శ్రీ
    0.27
    淈
    0.27
    ennessee
    0.27
    啄
    0.27
    മാക്കി
    0.25
    눴
    0.25
    𝔦
    0.25
    Ⲟ
    0.25
     revealed
    0.24
    Activations Density 0.003%

    No Known Activations