© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 236475
    Prev
    Next
    INDEX
    Explanations

    input_dim=, input_shape=

    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
     rel
    0.43
     Burg
    0.41
    !
    0.40
     Kevin
    0.40
    ↵↵
    0.40
     Duel
    0.39
     tan
    0.39
     Best
    0.39
    igt
    0.38
     Para
    0.38
    POSITIVE LOGITS
    ოლ
    0.50
    𝓵
    0.44
     starved
    0.44
    रेस्ट
    0.42
    穌
    0.40
     സ്വദേശ
    0.40
    媧
    0.40
     pastures
    0.39
     extruded
    0.39
    লাস
    0.39
    Activations Density 0.001%

    No Known Activations