© 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. 204515
    Prev
    Next
    INDEX
    Explanations

    technical or event descriptions

    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
    デ
    1.35
     デ
    1.34
    D
    1.17
     Dé
    1.16
     Де
    1.14
     Д
    1.13
    Де
    1.11
     D
    1.07
    Dé
    1.06
     डे
    1.05
    POSITIVE LOGITS
    秪
    0.36
    当た
    0.36
     divis
    0.35
     divination
    0.32
    Circ
    0.32
     disinvestment
    0.32
     அகற்ற
    0.32
     ओह
    0.32
    ﾊ
    0.31
     intensification
    0.30
    Activations Density 0.011%

    No Known Activations