© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 78209
    Prev
    Next
    INDEX
    Explanations

    formatting and code markers

    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
     sub
    0.36
    」「
    0.33
    ，“
    0.33
    "',
    0.33
     einer
    0.33
    彼
    0.33
     embl
    0.32
     “.
    0.32
     maig
    0.32
     propre
    0.32
    POSITIVE LOGITS
     النبي
    0.38
    滟
    0.35
    啷
    0.34
    腧
    0.34
    केमॉन
    0.33
    谶
    0.33
    로그
    0.33
    戛
    0.32
    曌
    0.32
    ಮಂತ್ರಿ
    0.32
    Activations Density 0.014%

    No Known Activations