© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 205900
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_20_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
     شہری
    0.35
    বাংলাদেশের
    0.33
    лийн
    0.33
    ੂ
    0.31
    脲
    0.30
    ]}/${
    0.30
     berhubungan
    0.30
    సం
    0.30
     평균
    0.30
    চিত্র
    0.29
    POSITIVE LOGITS
     such
    0.38
     as
    0.36
     since
    0.36
     \
    0.34
     Since
    0.34
     Each
    0.34
     Tesla
    0.34
     Not
    0.33
    ac
    0.33
     To
    0.33
    Activations Density 0.000%

    No Known Activations