© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 181272
    Prev
    Next
    INDEX
    Explanations

    questions asking why

    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_29_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
    undo
    0.39
    ukkig
    0.37
    versus
    0.36
     differs
    0.36
     `"
    0.35
    unique
    0.35
    一番
    0.35
     달라
    0.34
    joner
    0.34
    听
    0.34
    POSITIVE LOGITS
    এছাড়া
    0.43
     Berlusconi
    0.41
     astronomers
    0.41
    তবু
    0.41
     ЖК
    0.41
     screwed
    0.40
     भाज
    0.40
     rotator
    0.40
    Astronom
    0.40
     breaks
    0.39
    Activations Density 0.000%

    No Known Activations