© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 44037
    Prev
    Next
    INDEX
    Explanations

    URLs and foreign words

    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
     dart
    0.43
     gathered
    0.42
    REX
    0.40
    毅
    0.40
     stru
    0.39
     navigated
    0.39
    sanity
    0.38
     uttered
    0.38
    寤
    0.37
     infall
    0.37
    POSITIVE LOGITS
     Donde
    0.47
     Si
    0.45
     Otras
    0.44
     Sich
    0.43
    aturamento
    0.43
     Other
    0.42
     Otros
    0.42
     Są
    0.42
     Others
    0.41
     Punishment
    0.41
    Activations Density 0.001%

    No Known Activations