© 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. 14518
    Prev
    Next
    INDEX
    Explanations

    deafness, translation, translator

    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
     reinforcement
    0.49
     individ
    0.45
    (
    0.44
    ᱝ
    0.44
    ToEnd
    0.42
     monetization
    0.42
    Cert
    0.41
    zione
    0.40
     availability
    0.39
    pressure
    0.39
    POSITIVE LOGITS
     Nails
    0.52
    𝐑
    0.52
     chú
    0.51
    𝐇
    0.51
    ORY
    0.50
    daar
    0.49
     był
    0.48
    🗸
    0.48
    АР
    0.47
     ನೇ
    0.47
    Activations Density 0.020%

    No Known Activations