© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 107865
    Prev
    Next
    INDEX
    Explanations

    probably followed by something

    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_1_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
    å
    1.18
    에
    1.02
    nea
    0.83
    .$\
    0.82
    ế
    0.82
    ם
    0.82
     I
    0.80
    まり
    0.80
    〉
    0.79
    に
    0.77
    POSITIVE LOGITS
    ش
    1.48
    6
    1.37
    3
    1.26
     for
    1.22
    م
    1.21
    4
    1.12
    1
    1.11
    s
    1.09
    د
    1.09
    س
    1.08
    Activations Density 0.001%

    No Known Activations