© 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. 80165
    Prev
    Next
    INDEX
    Explanations

    improvements

    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
     architect
    0.41
    горе
    0.39
    mis
    0.38
     Verm
    0.35
     Hein
    0.35
     Reinh
    0.34
    <s>
    0.34
     Mis
    0.34
     sine
    0.34
     faire
    0.33
    POSITIVE LOGITS
     aba
    0.42
    encije
    0.42
     देखिएगा
    0.40
     tabpos
    0.40
     jee
    0.39
    搬型
    0.39
    indazole
    0.39
     SCIENCES
    0.39
    䄱
    0.39
    ｧ
    0.38
    Activations Density 0.005%

    No Known Activations