© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 78213
    Prev
    Next
    INDEX
    Explanations

    H

    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_53_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
     aldehyde
    0.45
     E
    0.42
    lgan
    0.39
     Ester
    0.39
     Poche
    0.38
    licz
    0.38
    actose
    0.38
     पॉ
    0.38
     Warsaw
    0.38
    Slider
    0.37
    POSITIVE LOGITS
     KK
    0.40
    絭
    0.38
     disruptions
    0.37
    अर
    0.37
     Sog
    0.37
    naked
    0.36
     immers
    0.36
     Naked
    0.35
    醌
    0.35
     naked
    0.35
    Activations Density 0.011%

    No Known Activations