© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 79241
    Prev
    Next
    INDEX
    Explanations

    will support

    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_29_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
     japanese
    0.44
     '}';
    0.41
     blister
    0.40
     proches
    0.40
    傲
    0.40
     ministers
    0.39
     ljudi
    0.39
     žmon
    0.39
    nyder
    0.38
     deque
    0.38
    POSITIVE LOGITS
     gerçekten
    0.42
    傷害
    0.37
    ‾
    0.37
     realmente
    0.36
     действительно
    0.36
    亟
    0.36
    KEY
    0.35
     вполне
    0.35
     மன்ற
    0.34
     здоров
    0.34
    Activations Density 0.001%

    No Known Activations