© 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. 170256
    Prev
    Next
    INDEX
    Explanations

    yield

    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
    Yield
    0.59
     yield
    0.51
    yield
    0.47
     Yield
    0.45
     yields
    0.44
    Worth
    0.41
    Minimal
    0.39
    .#
    0.39
    Waiting
    0.39
    Trong
    0.39
    POSITIVE LOGITS
     seguinte
    0.54
     jeune
    0.54
    s
    0.54
     passant
    0.42
     re
    0.41
     valle
    0.41
     jovem
    0.40
     joven
    0.39
     seguenti
    0.39
    surgical
    0.38
    Activations Density 0.000%

    No Known Activations