© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 43217
    Prev
    Next
    INDEX
    Explanations

    examples often listed after 'include'

    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_13_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
     tumours
    0.55
    ᵕ
    0.54
    Ⴀ
    0.51
    био
    0.48
    তেও
    0.46
     árvore
    0.46
     Presidente
    0.45
     commandments
    0.45
     রায়
    0.45
     architet
    0.45
    POSITIVE LOGITS
    ('');
    0.48
    dling
    0.47
    diss
    0.46
    out
    0.44
    speaking
    0.43
    stepping
    0.42
    ());
    0.42
    lag
    0.42
    ourcing
    0.41
    nom
    0.41
    Activations Density 0.116%

    No Known Activations