© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 13821
    Prev
    Next
    INDEX
    Explanations

    forms and transformations

    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
    Eating
    0.40
     izgled
    0.39
    Enroll
    0.38
    <unused72>
    0.38
     каких
    0.38
     फि
    0.37
     dao
    0.36
     источников
    0.36
     solemn
    0.36
    圜
    0.36
    POSITIVE LOGITS
     формы
    1.00
     forms
    0.99
     form
    0.97
     Forms
    0.95
    form
    0.86
     formes
    0.85
     Formen
    0.85
    Form
    0.84
    forms
    0.84
     formas
    0.82
    Activations Density 0.003%

    No Known Activations