© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 234813
    Prev
    Next
    INDEX
    Explanations

    error tracking

    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_46_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
    hoek
    0.43
     सूक्ष्म
    0.38
    齐
    0.38
    Hoist
    0.38
    𝙾
    0.38
    澥
    0.36
     Learned
    0.36
     distress
    0.36
    আন
    0.35
     altos
    0.35
    POSITIVE LOGITS
     S
    0.44
     sent
    0.42
     Ely
    0.40
     roll
    0.39
    New
    0.39
     scones
    0.39
    tung
    0.39
     scl
    0.38
    sent
    0.38
     furl
    0.37
    Activations Density 0.001%

    No Known Activations