© 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. 136042
    Prev
    Next
    INDEX
    Explanations

    success/error indicators

    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
    }_{+}
    0.38
     track
    0.36
    }`
    0.35
     volg
    0.35
    讐
    0.35
     Track
    0.34
     galactose
    0.34
     displayNumber
    0.34
     Chlorine
    0.34
     symbol
    0.33
    POSITIVE LOGITS
     Rest
    0.43
    Rest
    0.43
     फिज
    0.42
     REST
    0.40
     Legit
    0.40
    闲
    0.39
    厈
    0.38
     caracteres
    0.37
     Hei
    0.37
     forget
    0.36
    Activations Density 0.001%

    No Known Activations