© 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. 46020
    Prev
    Next
    INDEX
    Explanations

    generics

    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
    FromBody
    0.60
    it
    0.57
    a
    0.55
    }
    0.54
    //
    0.54
    ս
    0.52
    itance
    0.51
    ӳ
    0.51
    না
    0.50
    我对
    0.50
    POSITIVE LOGITS
     изменение
    0.60
    蓑
    0.55
     mongo
    0.55
     diferencia
    0.54
    MongoClient
    0.54
     demostrado
    0.53
     ря
    0.53
     коло
    0.53
     magneto
    0.53
     nome
    0.52
    Activations Density 0.008%

    No Known Activations