© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 179204
    Prev
    Next
    INDEX
    Explanations

    fn new

    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_24_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
     ert
    0.42
     characterize
    0.40
     Gonzalez
    0.40
    hmad
    0.39
    خراج
    0.37
    痛
    0.37
     "*.
    0.37
     McKenzie
    0.37
    dard
    0.36
    чого
    0.36
    POSITIVE LOGITS
     বৎস
    0.45
    ப்பதால்
    0.44
     hordes
    0.44
     حجم
    0.43
    arr
    0.43
     后
    0.42
    পান
    0.42
     água
    0.41
     Kotor
    0.41
    唷
    0.40
    Activations Density 0.000%

    No Known Activations