© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 139647
    Prev
    Next
    INDEX
    Explanations

    Hona hemen

    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
    i
    0.63
    jha
    0.55
    ́a
    0.54
     rumoured
    0.53
    ّى
    0.53
    它是
    0.52
    ؕ
    0.52
    t
    0.51
     muut
    0.50
    пі
    0.50
    POSITIVE LOGITS
     आंकड़ों
    0.75
    ish
    0.64
    emes
    0.59
     For
    0.58
    ude
    0.57
    ằng
    0.55
     hearings
    0.54
     powied
    0.54
    angu
    0.53
    ately
    0.53
    Activations Density 0.000%

    No Known Activations