© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 206790
    Prev
    Next
    INDEX
    Explanations

    access

    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
     inzwischen
    0.48
     теперь
    0.46
     પસંદ
    0.46
     jetzt
    0.45
    klady
    0.44
     крае
    0.43
     mittlerweile
    0.43
    圿
    0.42
     Кла
    0.42
     상세보기
    0.41
    POSITIVE LOGITS
     trich
    0.38
     hứng
    0.36
     sigmoid
    0.35
     mac
    0.34
     g
    0.34
     endorsing
    0.34
     reciprocal
    0.33
     glycer
    0.33
     qu
    0.33
     troch
    0.33
    Activations Density 0.000%

    No Known Activations