© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 163664
    Prev
    Next
    INDEX
    Explanations

    lazarus, blender, mine

    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_13_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
     bxa
    0.50
     Очень
    0.49
     каждая
    0.47
     Couldn
    0.47
     Василий
    0.46
     дал
    0.46
    ॓
    0.44
     разработ
    0.44
     Екатери
    0.44
     поло
    0.43
    POSITIVE LOGITS
    LED
    0.48
     modulate
    0.47
     humid
    0.46
    ಿಸ
    0.45
    許多
    0.44
     pastures
    0.44
     urb
    0.43
    ্যাটে
    0.43
    哋
    0.43
    stone
    0.41
    Activations Density 0.000%

    No Known Activations