© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 203897
    Prev
    Next
    INDEX
    Explanations

    winding roads

    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_37_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
    Crazy
    0.40
    Menus
    0.39
    ዴ
    0.39
     consci
    0.39
    ﹗
    0.38
    Chrome
    0.38
    セレ
    0.38
    狂
    0.38
    Decor
    0.38
    Embarked
    0.38
    POSITIVE LOGITS
     steep
    0.46
     steeper
    0.45
     steeply
    0.44
     발표
    0.41
     stairway
    0.41
    屋外
    0.41
    োদয়
    0.40
     setback
    0.40
     outdoor
    0.39
     curving
    0.39
    Activations Density 0.003%

    No Known Activations