© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 175787
    Prev
    Next
    INDEX
    Explanations

    base of geometric shapes

    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
    posable
    0.40
     સલા
    0.37
    발
    0.37
    平台
    0.37
     rappresenta
    0.37
    batas
    0.37
     dvara
    0.37
     finally
    0.36
     আসবে
    0.36
     передви
    0.36
    POSITIVE LOGITS
    锕
    0.43
    icult
    0.40
     antiqu
    0.39
     flint
    0.37
    inken
    0.37
     ente
    0.36
    λλην
    0.35
     opiek
    0.35
    ención
    0.35
     étn
    0.34
    Activations Density 0.000%

    No Known Activations