© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 197182
    Prev
    Next
    INDEX
    Explanations

    igh

    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_50_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
    牡
    0.46
    ത്തരം
    0.43
    jelasan
    0.42
    প্রিয়
    0.40
     rusting
    0.40
    jak
    0.38
    glich
    0.37
     thawing
    0.37
     उल्लेख
    0.37
    hrt
    0.37
    POSITIVE LOGITS
    ილები
    0.39
    consin
    0.38
     ex
    0.38
    엑
    0.38
    Enc
    0.37
    offsetWidth
    0.37
     Ex
    0.37
    BuildConfig
    0.37
    éné
    0.36
     Asa
    0.36
    Activations Density 0.001%

    No Known Activations