© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 89309
    Prev
    Next
    INDEX
    Explanations

    numbers in lists or code

    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_23_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
     Nightingale
    0.40
    flatten
    0.37
    <0x0D>
    0.37
     Boeing
    0.36
     arsenal
    0.36
    orgeous
    0.36
     (
    0.36
     fairs
    0.36
     through
    0.35
     tulis
    0.35
    POSITIVE LOGITS
     ताब्यात
    0.45
    દિવસ
    0.44
    дія
    0.43
     خواتین
    0.42
     ದಿನ
    0.41
    خر
    0.40
     contradicted
    0.40
     жінок
    0.40
    ؑ
    0.40
     dimerization
    0.40
    Activations Density 0.000%

    No Known Activations