© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 214565
    Prev
    Next
    INDEX
    Explanations

    under

    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_47_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
     parten
    0.42
    मनी
    0.39
     പഞ്ചായ
    0.39
    ாச
    0.38
     phản
    0.38
    Coat
    0.37
    probabilities
    0.37
    埧
    0.37
     Working
    0.36
    Curt
    0.36
    POSITIVE LOGITS
    ))),
    0.41
     کریں
    0.38
    ەکانی
    0.37
    电气
    0.37
    ောက်
    0.37
    弱い
    0.37
    IENT
    0.36
    akan
    0.36
    விய
    0.36
     robust
    0.36
    Activations Density 0.001%

    No Known Activations