© 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. 206929
    Prev
    Next
    INDEX
    Explanations

    character names or identifiers

    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
    compassing
    0.40
    vening
    0.39
    ก
    0.38
    ου
    0.36
    יו
    0.35
     הראשון
    0.34
    overlapping
    0.34
     Первый
    0.34
     enveloping
    0.34
    ัจ
    0.32
    POSITIVE LOGITS
     dishonest
    0.38
     redir
    0.37
     නි
    0.36
     corretamente
    0.36
     AMPL
    0.36
     igen
    0.35
     හේ
    0.35
     bha
    0.34
     jól
    0.34
     被
    0.33
    Activations Density 0.001%

    No Known Activations