© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 2308
    Prev
    Next
    INDEX
    Explanations

    function, evidence, production

    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_39_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
    Model
    0.43
    Dichloro
    0.41
    Maximize
    0.41
    栅
    0.41
     maximizes
    0.39
     modeled
    0.39
    нець
    0.39
     Couples
    0.38
     모델
    0.38
    Models
    0.38
    POSITIVE LOGITS
    க்கா
    0.43
     रणवीर
    0.38
     दस्तावेज
    0.37
     列
    0.37
     episode
    0.37
     PASS
    0.37
    decomposition
    0.36
     episodes
    0.36
     episódio
    0.35
     एवरेज
    0.35
    Activations Density 0.060%

    No Known Activations