© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 176646
    Prev
    Next
    INDEX
    Explanations

    what's on your mind

    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
    íos
    0.34
    oed
    0.28
    ίνουν
    0.28
    毽
    0.27
    アルバ
    0.26
     político
    0.26
    ormány
    0.25
    lacian
    0.25
    胿
    0.24
     Political
    0.24
    POSITIVE LOGITS
    Milk
    0.29
    وت
    0.26
    TryParse
    0.26
     दूध
    0.26
     broadest
    0.26
     hasta
    0.25
    교육
    0.25
     spie
    0.25
    得知
    0.25
     Milch
    0.25
    Activations Density 0.002%

    No Known Activations