© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 134664
    Prev
    Next
    INDEX
    Explanations

    code structure or programming logic

    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
    izophren
    0.42
    Sep
    0.42
    ineuses
    0.42
     قريب
    0.40
    鸚
    0.39
    Iris
    0.37
     Sahib
    0.37
     پار
    0.37
     Dishes
    0.36
    織
    0.36
    POSITIVE LOGITS
     urgency
    0.44
    嗟
    0.40
     want
    0.39
    GF
    0.38
    무
    0.38
     priorit
    0.37
    practical
    0.36
     cautious
    0.36
     fores
    0.36
     Practical
    0.36
    Activations Density 0.000%

    No Known Activations