© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 258851
    Prev
    Next
    INDEX
    Explanations

    functionality and operation

    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_22_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
    جب
    0.39
    legen
    0.38
    גן
    0.38
    لم
    0.38
     tandem
    0.38
    гө
    0.37
    لام
    0.37
    迦
    0.36
    jado
    0.35
    لما
    0.35
    POSITIVE LOGITS
     मल्टीप्लाई
    0.45
     భారీ
    0.42
     quindi
    0.41
     국제
    0.40
    юр
    0.40
     ရက်
    0.39
     इंटरनेशनल
    0.38
    𝘧
    0.38
     veľ
    0.38
    Lik
    0.38
    Activations Density 0.001%

    No Known Activations