© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 100429
    Prev
    Next
    INDEX
    Explanations

    access tokens

    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_14_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
     theatre
    0.52
     literary
    0.52
     grain
    0.52
    ர
    0.51
    ራዊ
    0.50
     currentUser
    0.49
     théâtre
    0.49
     সাহিত্য
    0.49
     బె
    0.49
    unoscut
    0.48
    POSITIVE LOGITS
     pedals
    0.54
    вел
    0.50
    ത്വ
    0.48
    pell
    0.47
    2
    0.46
    akala
    0.46
    GAAP
    0.45
    Code
    0.45
    ों
    0.45
    مو
    0.44
    Activations Density 0.000%

    No Known Activations