© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 105568
    Prev
    Next
    INDEX
    Explanations

    primary

    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_44_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
    izat
    0.41
     Belf
    0.41
    柊
    0.40
    isas
    0.39
    azas
    0.39
    iza
    0.38
    izzate
    0.38
     ভীত
    0.38
    ionized
    0.38
    ➋
    0.38
    POSITIVE LOGITS
     reap
    0.42
    珅
    0.40
    ppable
    0.38
    Press
    0.38
     temple
    0.36
    례
    0.36
    жли
    0.36
    级
    0.35
     Valid
    0.35
     alloc
    0.35
    Activations Density 0.000%

    No Known Activations