© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 214901
    Prev
    Next
    INDEX
    Explanations

    given

    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_47_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
    oggia
    0.47
     psig
    0.43
    ermos
    0.40
    脘
    0.40
    ANN
    0.39
     pistols
    0.39
    ỡng
    0.38
    vii
    0.37
    CONH
    0.37
    polls
    0.37
    POSITIVE LOGITS
     [
    0.44
     Production
    0.40
    ))[
    0.40
    Herbert
    0.39
    }[
    0.39
     Eingang
    0.39
     [#
    0.38
    }[\
    0.38
     Herbert
    0.37
     қу
    0.37
    Activations Density 0.005%

    No Known Activations