© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 50415
    Prev
    Next
    INDEX
    Explanations

    where is it?

    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_30_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
     ต่าง
    0.37
    茫
    0.37
    prova
    0.35
     Lopes
    0.34
     toes
    0.34
    leit
    0.34
     whistles
    0.34
     являются
    0.34
     whistle
    0.33
     Legs
    0.33
    POSITIVE LOGITS
    CompliancePolicy
    0.46
    aniach
    0.43
    Plenty
    0.42
    镞
    0.40
    Anybody
    0.40
    rahm
    0.40
    اعة
    0.39
    MERS
    0.39
    াবির
    0.39
     फ्लावर
    0.39
    Activations Density 0.003%

    No Known Activations