© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 34783
    Prev
    Next
    INDEX
    Explanations

    a lot followed by of or depends

    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_3_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
     e
    0.64
    ύ
    0.64
    ър
    0.61
    اني
    0.60
     més
    0.58
    ará
    0.58
    ă
    0.58
     sobre
    0.57
    ني
    0.57
    ます
    0.56
    POSITIVE LOGITS
     Progressive
    0.68
    t
    0.64
    Gloss
    0.62
    inud
    0.61
     Pengh
    0.61
    ド
    0.60
     Jake
    0.59
     Neg
    0.59
     Komple
    0.59
    tiin
    0.59
    Activations Density 0.001%

    No Known Activations