© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 109675
    Prev
    Next
    INDEX
    Explanations

    toaster

    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_2_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
    amad
    1.02
    ari
    1.00
    ungan
    0.99
    ästä
    0.97
    ape
    0.96
    äksi
    0.96
    ong
    0.90
    े
    0.90
    ara
    0.89
     the
    0.89
    POSITIVE LOGITS
    t
    1.50
    r
    1.28
    x
    1.19
    y
    1.17
    d
    1.16
    ر
    1.15
    ม
    1.14
    z
    1.09
    מ
    1.09
     I
    1.06
    Activations Density 0.000%

    No Known Activations