© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 106784
    Prev
    Next
    INDEX
    Explanations

    featuring item

    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_1_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
    us
    1.20
    ת
    1.18
    ت
    1.13
    y
    1.09
    ва
    1.08
    in
    1.05
     to
    1.00
    י
    0.97
    ა
    0.95
    一颗
    0.95
    POSITIVE LOGITS
    ला
    0.97
     lequel
    0.95
     hvilket
    0.91
     lesquels
    0.89
    이다
    0.85
    না
    0.84
    O
    0.82
    AccessToken
    0.80
     extremamente
    0.80
     elenc
    0.80
    Activations Density 0.001%

    No Known Activations