© 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. 142412
    Prev
    Next
    INDEX
    Explanations

    vector initialization syntax

    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
    a
    2.67
    n
    1.93
    i
    1.60
    ot
    1.45
    l
    1.45
    া
    1.44
    the
    1.43
    ा
    1.41
    puede
    1.41
    o
    1.41
    POSITIVE LOGITS
    л
    1.48
    I
    1.26
    м
    1.23
    о
    1.23
    ए
    1.23
    И
    1.23
     aneurysm
    1.21
    ৬
    1.21
    ل
    1.19
     decentral
    1.18
    Activations Density 0.001%

    No Known Activations