© 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. 77860
    Prev
    Next
    INDEX
    Explanations

    state

    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
     うち
    0.43
    溘
    0.39
     Devon
    0.39
     cork
    0.39
     Ryan
    0.38
     kenn
    0.38
    Ryan
    0.38
    -}
    0.36
    㮆
    0.36
    platinum
    0.36
    POSITIVE LOGITS
    atique
    0.39
     DAMAGES
    0.38
    ہر
    0.37
     tanı
    0.36
    aciju
    0.36
    しまいました
    0.36
     upravo
    0.35
    ovanje
    0.34
    ہوں
    0.34
     wor
    0.34
    Activations Density 0.000%

    No Known Activations