© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 34500
    Prev
    Next
    INDEX
    Explanations

    question:

    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_7_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
    AR
    0.49
    ali
    0.48
    ،
    0.48
     teamwork
    0.47
    O
    0.47
    U
    0.46
    IL
    0.45
    i
    0.44
     revital
    0.44
     telefone
    0.44
    POSITIVE LOGITS
    <unused2018>
    0.52
     andRow
    0.52
    ниці
    0.51
    كره
    0.49
     фаразы
    0.47
    ни
    0.47
     are
    0.47
    <0x80>
    0.47
    <unused2168>
    0.46
    艿
    0.46
    Activations Density 0.048%

    No Known Activations