© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 179743
    Prev
    Next
    INDEX
    Explanations

    requests.exceptions

    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
     أك
    0.44
    VAT
    0.43
    জ্জামান
    0.42
    legd
    0.42
    𝖑
    0.41
    ød
    0.41
     provoz
    0.41
    Thou
    0.41
    ย์
    0.40
     hypersur
    0.40
    POSITIVE LOGITS
     L
    0.44
     Ps
    0.41
     Priority
    0.41
     County
    0.39
     Porta
    0.39
    ps
    0.39
     Mud
    0.38
     quản
    0.38
    ემი
    0.38
     county
    0.38
    Activations Density 0.001%

    No Known Activations