© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 43115
    Prev
    Next
    INDEX
    Explanations

    parts of clothing or furniture

    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
     devem
    0.54
    dont
    0.54
     सामील
    0.54
    p
    0.53
    entine
    0.52
     disobey
    0.52
    ın
    0.49
    ప
    0.49
     arrivent
    0.49
     dont
    0.48
    POSITIVE LOGITS
    ет
    0.49
    お願いします
    0.47
     Chesapeake
    0.45
    ре
    0.44
     Very
    0.42
     pisos
    0.42
     java
    0.42
     WORDS
    0.42
     Scop
    0.40
     Malta
    0.40
    Activations Density 0.025%

    No Known Activations