© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 236543
    Prev
    Next
    INDEX
    Explanations

    Centaur

    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
     F
    0.70
    F
    0.55
     ফ
    0.47
     P
    0.44
     Eb
    0.43
    human
    0.42
    ఎఫ్
    0.42
    xF
    0.42
     HUMAN
    0.42
     الف
    0.41
    POSITIVE LOGITS
     cent
    0.39
     stolen
    0.38
     centr
    0.37
    ﻠ
    0.37
     doubling
    0.36
    Chromatic
    0.36
    aison
    0.36
     ब्ले
    0.36
    Modal
    0.35
     sapon
    0.35
    Activations Density 0.001%

    No Known Activations