© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 205700
    Prev
    Next
    INDEX
    Explanations

    dialogue reported speech

    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_25_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
     cre
    0.17
     моче
    0.16
     clas
    0.16
     ро
    0.15
     impermeable
    0.15
     դ
    0.15
    клад
    0.15
    INTRESOURCE
    0.15
     ሰ
    0.15
     wie
    0.15
    POSITIVE LOGITS
         
    0.15
    ન્ટ
    0.15
     மற்றொரு
    0.14
    na
    0.14
    ग्रेड
    0.14
     Valerie
    0.14
     harta
    0.14
    izada
    0.14
     negligence
    0.14
     অভিযোগে
    0.13
    Activations Density 0.001%

    No Known Activations