© 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. 82673
    Prev
    Next
    INDEX
    Explanations

    wa

    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
    اق
    0.40
     R
    0.38
    اقه
    0.38
     అమ్మ
    0.37
    ipart
    0.37
     Rocha
    0.35
     aerial
    0.35
     субъек
    0.35
     encompassed
    0.35
    胱
    0.35
    POSITIVE LOGITS
     localtime
    0.43
    涪
    0.42
     pencil
    0.40
     Hearth
    0.39
     rundown
    0.39
     Suicide
    0.38
    EditDialogOpen
    0.38
     billiard
    0.38
     வால்பேப்பர்
    0.38
     Pencil
    0.38
    Activations Density 0.001%

    No Known Activations