© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 11390
    Prev
    Next
    INDEX
    Explanations

    code structure: variable = value

    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_40_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
     আশা
    0.38
     balanced
    0.38
     Тыва
    0.36
     forgiven
    0.36
    ampunk
    0.36
    ாரு
    0.35
    愉快
    0.35
    麼
    0.35
    Verbose
    0.35
     اتمنى
    0.35
    POSITIVE LOGITS
     TRANS
    0.41
     CON
    0.40
    INTE
    0.39
    OFF
    0.39
     EXPL
    0.39
    MEDI
    0.38
     STR
    0.38
    ΰ
    0.38
     INTEGR
    0.38
     IND
    0.37
    Activations Density 0.056%

    No Known Activations