© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 105410
    Prev
    Next
    INDEX
    Explanations

    comienza a

    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
    ről
    1.14
    u
    1.11
    یت
    1.10
     columnName
    1.09
    ও
    1.07
    ્સ
    1.05
    র
    1.02
     estrogen
    1.01
     mesmos
    1.01
     zucchero
    1.01
    POSITIVE LOGITS
    x
    1.63
    H
    1.56
    A
    1.53
    P
    1.53
    Y
    1.53
    M
    1.52
    E
    1.41
    O
    1.40
    for
    1.37
    خ
    1.37
    Activations Density 0.000%

    No Known Activations