© 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. 89005
    Prev
    Next
    INDEX
    Explanations

    following are

    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
    اد
    0.73
    ad
    0.71
    स्‍या
    0.63
     r
    0.62
     tập
    0.57
     ff
    0.57
    ESH
    0.56
     رس
    0.56
     by
    0.55
     Hz
    0.55
    POSITIVE LOGITS
    ίων
    0.63
    рия
    0.58
    velopp
    0.55
    ações
    0.54
    પો
    0.54
    Brightness
    0.54
    ﻭ
    0.54
    rictional
    0.52
     recieve
    0.52
    urrence
    0.51
    Activations Density 0.002%

    No Known Activations