© 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. 2295
    Prev
    Next
    INDEX
    Explanations

    Integrated

    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
    轨
    0.40
    гото
    0.39
    CollectedField
    0.38
     goblet
    0.36
     fal
    0.35
     Cuban
    0.35
     Cuba
    0.35
     Combined
    0.35
    గర
    0.35
     participe
    0.35
    POSITIVE LOGITS
    Кар
    0.39
    opes
    0.38
    adapted
    0.38
     Цер
    0.36
     Kor
    0.36
    Ꮶ
    0.36
     PEP
    0.35
     eks
    0.35
     сооб
    0.35
     Eks
    0.35
    Activations Density 0.002%

    No Known Activations