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

    Neuronpedia

    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. 206739
    Prev
    Next
    INDEX
    Explanations

    comparison operator

    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
    uria
    0.41
    vino
    0.40
    vex
    0.40
    razione
    0.38
    ria
    0.38
    avia
    0.38
    ត
    0.38
     assolutamente
    0.38
    WITH
    0.37
    anic
    0.37
    POSITIVE LOGITS
    ጕ
    0.38
     Configure
    0.37
     executions
    0.37
     hadc
    0.37
     incidences
    0.37
     discourage
    0.36
     Viewed
    0.36
     Collaborate
    0.35
     regressions
    0.35
     interference
    0.34
    Activations Density 0.000%

    No Known Activations