© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 229279
    Prev
    Next
    INDEX
    Explanations

    0

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_57_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
    izem
    0.42
    ojana
    0.41
    えば
    0.40
    iseur
    0.38
    社の
    0.38
    샥
    0.36
    ude
    0.36
    িলারা
    0.36
    бие
    0.36
    ostar
    0.36
    POSITIVE LOGITS
    lbs
    0.40
    mmHg
    0.39
    @"
    0.38
     tendría
    0.38
    trace
    0.37
     ګټ
    0.36
    [.
    0.36
    Quarter
    0.36
    Mà
    0.36
    Applicant
    0.35
    Activations Density 0.000%

    No Known Activations