© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 97948
    Prev
    Next
    INDEX
    Explanations

    Fiver, JavaScript, Venture Capital

    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_14_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
     shortage
    0.44
     Aar
    0.44
     echoing
    0.44
     azot
    0.43
     alanine
    0.43
     veri
    0.43
     tunggu
    0.43
    螌
    0.43
     percaya
    0.43
     tegas
    0.42
    POSITIVE LOGITS
    VS
    0.56
    id
    0.53
    world
    0.53
    WALL
    0.52
    ון
    0.51
    ogl
    0.50
    root
    0.48
    VM
    0.47
    let
    0.46
    end
    0.46
    Activations Density 0.000%

    No Known Activations