© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 176205
    Prev
    Next
    INDEX
    Explanations

    C++ time header

    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_20_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
    sq
    0.44
    閤
    0.43
    ूंकि
    0.41
     Lotto
    0.40
    suite
    0.40
    ⽅
    0.40
    rock
    0.39
     sq
    0.38
    owod
    0.38
    ્ર
    0.38
    POSITIVE LOGITS
     isotropy
    0.55
     aniline
    0.50
     patina
    0.49
     apel
    0.49
    霽
    0.48
     antérieure
    0.48
     iris
    0.47
     permukaan
    0.46
     birt
    0.46
     argento
    0.46
    Activations Density 0.000%

    No Known Activations