© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 38772
    Prev
    Next
    INDEX
    Explanations

    convert to json

    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_11_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
     f
    0.70
     i
    0.68
     U
    0.63
     Uk
    0.62
    nar
    0.59
     S
    0.59
    nd
    0.59
     <
    0.59
    uk
    0.59
     Iw
    0.59
    POSITIVE LOGITS
    PrototypeOf
    0.66
    ה
    0.64
    その
    0.60
    🤷
    0.55
    考え
    0.54
    Silicon
    0.54
    प
    0.53
    ด
    0.53
    ב
    0.52
    ﹊
    0.52
    Activations Density 0.001%

    No Known Activations