© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 158339
    Prev
    Next
    INDEX
    Explanations

    skin

    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_2_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
    н
    1.25
     projet
    0.98
    ИС
    0.95
    р
    0.90
    zuoye
    0.86
     stoichi
    0.84
    Α
    0.84
     PAOK
    0.83
     thermoelectric
    0.83
    ╅
    0.82
    POSITIVE LOGITS
    lık
    1.32
     in
    1.16
    ர்கள்
    1.16
    lng
    1.15
    ary
    1.12
    ant
    1.09
    ون
    1.09
    0
    1.07
     înce
    1.06
    lardan
    1.05
    Activations Density 0.000%

    No Known Activations