© 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. 134813
    Prev
    Next
    INDEX
    Explanations

    messed up

    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
    ed
    1.58
    n
    1.58
    et
    1.45
    ।
    1.40
    ır
    1.34
    al
    1.30
    ing
    1.30
    y
    1.27
    in
    1.24
    ae
    1.22
    POSITIVE LOGITS
    ון
    0.90
    もの
    0.85
    ث
    0.83
     headset
    0.83
    να
    0.80
     storied
    0.80
    šina
    0.79
    ONA
    0.78
    סי
    0.76
    দের
    0.75
    Activations Density 0.001%

    No Known Activations