© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 80091
    Prev
    Next
    INDEX
    Explanations

    CSS/Sass code

    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
     `:
    0.37
     haar
    0.35
     collusion
    0.35
     gecko
    0.35
     бу
    0.35
    rafish
    0.35
    ge
    0.34
     ఆమె
    0.34
     അവളുടെ
    0.34
     //-->
    0.34
    POSITIVE LOGITS
     lô
    0.39
     naby
    0.36
    apay
    0.36
    ত্র
    0.35
    পত্র
    0.35
     má
    0.34
    khov
    0.34
    Máy
    0.34
     Late
    0.34
    Arkadaşlar
    0.34
    Activations Density 0.000%

    No Known Activations