© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 107998
    Prev
    Next
    INDEX
    Explanations

    here followed by punctuation

    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_1_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
    t
    1.87
    نا
    1.41
    ни
    1.17
    ج
    1.13
    на
    1.13
    na
    1.13
    l
    1.06
    ni
    1.05
    c
    1.05
    nu
    1.04
    POSITIVE LOGITS
    -
    1.07
    ;//
    1.05
     =-
    1.03
     καθώς
    1.02
     objected
    1.01
     crebre
    0.96
    ме
    0.96
     outlying
    0.96
     exertions
    0.95
    ;
    0.94
    Activations Density 0.003%

    No Known Activations