© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 237181
    Prev
    Next
    INDEX
    Explanations

    inner loop

    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_25_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
     뿐
    0.47
     traditions
    0.40
     മാത്രമല്ല
    0.40
    뿐
    0.40
     традиции
    0.39
    近年来
    0.38
     тради
    0.38
    Trad
    0.38
     ఇంత
    0.38
     மட்டுமல்ல
    0.38
    POSITIVE LOGITS
     HL
    0.41
    莗
    0.37
     thể
    0.36
     inicialmente
    0.36
    जरीवाल
    0.35
    സ്സ
    0.35
    FirstOrDefault
    0.35
    ებენ
    0.34
    驍
    0.34
     Springfield
    0.33
    Activations Density 0.001%

    No Known Activations