© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 52491
    Prev
    Next
    INDEX
    Explanations

    vibes

    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_55_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
     राजकीय
    0.39
     takes
    0.38
    abbanti
    0.37
    RegistrationBean
    0.37
    侵
    0.37
    avais
    0.37
     cat
    0.36
     rend
    0.36
    鹕
    0.36
     Took
    0.36
    POSITIVE LOGITS
    vib
    0.41
     vibes
    0.39
    Ideas
    0.39
     archive
    0.38
     Goals
    0.38
     Style
    0.38
    Computing
    0.38
     مبلغ
    0.38
     Vibes
    0.37
     série
    0.37
    Activations Density 0.013%

    No Known Activations