© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 79765
    Prev
    Next
    INDEX
    Explanations

    median calculation

    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_0_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
    ي
    1.66
    ك
    1.44
    在
    1.40
    ),
    1.34
    ი
    1.34
    kter
    1.30
    们的
    1.16
    )
    1.16
    i
    1.12
    kost
    1.11
    POSITIVE LOGITS
    ل
    1.87
    5
    1.60
    or
    1.55
    ore
    1.51
    ä
    1.49
    ov
    1.46
    л
    1.45
    n
    1.44
    us
    1.42
    4
    1.41
    Activations Density 0.002%

    No Known Activations