© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 116635
    Prev
    Next
    INDEX
    Explanations

    performance for its size

    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_27_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
     optionally
    0.45
    
    0.41
     ነው።
    0.40
     پاب
    0.38
     በመ
    0.38
     በፍ
    0.38
     Average
    0.37
     voluntarily
    0.37
    合わせて
    0.37
    менен
    0.36
    POSITIVE LOGITS
    īn
    0.45
     unwell
    0.44
     Presidency
    0.39
    ových
    0.39
    ෙ
    0.39
     siège
    0.38
     scrive
    0.38
    etal
    0.37
    れていた
    0.37
    ispens
    0.37
    Activations Density 0.002%

    No Known Activations