© 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. 61501
    Prev
    Next
    INDEX
    Explanations

    brands

    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
    ne
    1.30
    .
    1.28
    大
    1.23
    7
    1.21
    بد
    1.19
    ला
    1.16
    ون
    1.16
    на
    1.15
     ότι
    1.13
    8
    1.11
    POSITIVE LOGITS
    is
    1.48
    n
    1.41
    s
    1.30
    y
    1.27
    in
    1.15
    l
    1.15
    nimmt
    1.13
    ᱐
    1.13
    هي
    1.13
    ០
    1.13
    Activations Density 0.002%

    No Known Activations