© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 241895
    Prev
    Next
    INDEX
    Explanations

    difficulty, potential, effort, score

    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_25_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
     attachments
    0.42
    喁
    0.42
     Footer
    0.40
    ουμε
    0.40
    Server
    0.39
     interiors
    0.39
     goodies
    0.39
     pizzas
    0.38
    ites
    0.38
     couplings
    0.38
    POSITIVE LOGITS
    沫
    0.37
     Lehman
    0.37
     الخامس
    0.36
     indu
    0.35
     दूसरा
    0.35
     Kasım
    0.34
    投资
    0.33
     लाभदायक
    0.33
    नेश्वर
    0.33
    хова
    0.33
    Activations Density 0.008%

    No Known Activations