© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 210607
    Prev
    Next
    INDEX
    Explanations

    all possible paths

    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_5_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
     a
    0.96
     I
    0.86
    usele
    0.85
    urs
    0.84
    ivi
    0.84
    ier
    0.83
     주는
    0.81
     불구하고
    0.80
    inar
    0.80
     Theme
    0.80
    POSITIVE LOGITS
    (
    1.60
    er
    1.45
    u
    1.34
    ון
    1.31
    é
    1.26
    一
    1.19
    ク
    1.16
    ле
    1.10
     activación
    1.10
    가능
    1.09
    Activations Density 0.001%

    No Known Activations