© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 5511
    Prev
    Next
    INDEX
    Explanations

    program, combine, walking

    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_39_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
    alahan
    0.38
     podm
    0.38
    মুখী
    0.38
    덜
    0.37
    ály
    0.37
    LastGen
    0.37
    တာ
    0.35
    μάτων
    0.35
     היו
    0.35
    παϊ
    0.35
    POSITIVE LOGITS
    負荷
    0.41
    renaline
    0.40
    齐
    0.40
    বঙ্গের
    0.39
     satisfied
    0.38
     뭘
    0.38
     اقبال
    0.37
    前进
    0.37
    ⇤
    0.37
     hold
    0.36
    Activations Density 0.108%

    No Known Activations