© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 62213
    Prev
    Next
    INDEX
    Explanations

    Scout and adult roles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_11_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
     /
    0.45
     +
    0.45
     negócio
    0.41
     $+
    0.41
     FAX
    0.40
     terminus
    0.40
    usus
    0.40
    _{
    0.40
     '
    0.40
    lf
    0.39
    POSITIVE LOGITS
    ্যালে
    0.47
    кисло
    0.47
     CheckException
    0.47
    roft
    0.46
    aluminum
    0.46
     hoher
    0.45
     ઘણા
    0.45
     Многие
    0.45
     ஐந்து
    0.45
    钛
    0.45
    Activations Density 0.013%

    No Known Activations