© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 10143
    Prev
    Next
    INDEX
    Explanations

    addresses and street names

    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_13_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
     pr
    0.39
     tagline
    0.37
     kä
    0.37
     ksi
    0.37
     keywords
    0.36
    ิทธิภาพ
    0.36
     ;
    0.36
     $
    0.35
     mots
    0.35
     SEP
    0.35
    POSITIVE LOGITS
    ombie
    0.41
    addin
    0.41
    ମ
    0.40
     улице
    0.39
    ອອກ
    0.39
    付ける
    0.37
    тической
    0.37
    ໊
    0.37
    ivative
    0.37
    대학
    0.36
    Activations Density 0.021%

    No Known Activations