© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 87345
    Prev
    Next
    INDEX
    Explanations

    Eloquent model relationships function

    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
     poput
    0.41
    霍
    0.41
     fierce
    0.40
    ම්
    0.39
     jorn
    0.39
     Tiến
    0.39
    امین
    0.39
     Telegraph
    0.39
    تهای
    0.39
     Naomi
    0.38
    POSITIVE LOGITS
    ঝ
    0.41
     Же
    0.41
    Combining
    0.40
     পেয়েছে
    0.38
     welcher
    0.38
    parametric
    0.38
     smoothness
    0.37
    espresso
    0.36
     باقی
    0.36
    properties
    0.35
    Activations Density 0.000%

    No Known Activations