© 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. 84102
    Prev
    Next
    INDEX
    Explanations

    this followed by issues

    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
     직접
    0.32
    ক্তি
    0.31
     woorden
    0.30
    ๎
    0.30
     feeds
    0.29
    인트
    0.29
    हीत
    0.29
     వ్యక్
    0.29
    для
    0.29
     word
    0.29
    POSITIVE LOGITS
     prestig
    0.38
     Mog
    0.37
    IMA
    0.35
     د
    0.35
     düny
    0.34
     praised
    0.34
     chilly
    0.33
     दुनिया
    0.33
     Popular
    0.33
     RI
    0.32
    Activations Density 0.028%

    No Known Activations