© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 113010
    Prev
    Next
    INDEX
    Explanations

    take over

    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_2_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
    o
    1.23
    m
    1.22
    ed
    1.13
    k
    1.09
    ла
    1.09
    takes
    1.08
     on
    1.06
    deki
    1.06
    tj
    1.05
    gister
    1.05
    POSITIVE LOGITS
    大
    0.97
    fade
    0.83
    .</
    0.80
    어졌
    0.80
    вча
    0.79
     relive
    0.79
     нём
    0.79
    ۰
    0.79
     groan
    0.78
     grotesque
    0.77
    Activations Density 0.001%

    No Known Activations