© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 41639
    Prev
    Next
    INDEX
    Explanations

    how to define or build relationships

    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
    ,$
    0.45
     comment
    0.40
    һ
    0.39
    COMMENT
    0.39
    ילו
    0.38
     Ö
    0.38
    ILITY
    0.37
     salicylate
    0.36
     здра
    0.36
     соль
    0.36
    POSITIVE LOGITS
     आकर्षक
    0.47
     dijel
    0.46
    舅
    0.43
    மல்
    0.42
    Uuid
    0.42
    Lead
    0.41
    Loren
    0.41
     ადგილ
    0.41
    ሎ
    0.41
    Structured
    0.40
    Activations Density 0.048%

    No Known Activations