© 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. 45223
    Prev
    Next
    INDEX
    Explanations

    acknowledging, asking, trying, described, owed

    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
     versions
    0.34
     deeds
    0.33
     adaptations
    0.33
     replacements
    0.33
     путем
    0.32
    改正
    0.32
     apologised
    0.32
    膈
    0.32
    гать
    0.31
     solvers
    0.31
    POSITIVE LOGITS
     Sozial
    0.35
     অস্ত্রের
    0.35
    Ⅸ
    0.34
     Robotics
    0.33
     Psik
    0.33
    ɭ
    0.33
     nő
    0.33
    莒
    0.33
     tessuto
    0.33
     বৈদ্য
    0.33
    Activations Density 0.007%

    No Known Activations