© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 205221
    Prev
    Next
    INDEX
    Explanations

    datapad

    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_56_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
    groupBox
    0.38
    ¿
    0.37
     th
    0.35
    <unused990>
    0.35
     Pelt
    0.33
    赛
    0.33
     দ্বারা
    0.31
    ष्ण
    0.31
     pouch
    0.31
     služby
    0.31
    POSITIVE LOGITS
    ىن
    0.38
    ework
    0.36
    ewords
    0.35
    eroy
    0.35
    ൽക
    0.35
    ewel
    0.34
    eword
    0.33
    eweg
    0.32
    眝
    0.32
    ewise
    0.31
    Activations Density 0.002%

    No Known Activations