© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 206104
    Prev
    Next
    INDEX
    Explanations

    company

    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_6_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
    s
    1.49
    ed
    1.30
    c
    1.29
    g
    1.22
    er
    1.19
    i
    1.14
    त
    1.13
    la
    1.10
    O
    1.10
     indiquer
    1.08
    POSITIVE LOGITS
     be
    1.01
    рт
    0.97
    "
    0.89
     храм
    0.85
    ội
    0.80
     статье
    0.80
    рта
    0.79
     longstanding
    0.78
    นาน
    0.77
    akers
    0.76
    Activations Density 0.000%

    No Known Activations