© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 241483
    Prev
    Next
    INDEX
    Explanations

    host and domain names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_25_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
    bodied
    0.41
    _
    0.40
     conversions
    0.40
    variables
    0.37
     să
    0.36
     każdej
    0.36
    тей
    0.36
    żyw
    0.36
    ز
    0.36
     پیدا
    0.36
    POSITIVE LOGITS
     rufis
    0.45
    欬
    0.36
     amiss
    0.36
     broch
    0.35
     tl
    0.35
     шла
    0.35
     tumour
    0.34
     citiz
    0.34
     cures
    0.34
    ल्ला
    0.34
    Activations Density 0.000%

    No Known Activations