© 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. 10879
    Prev
    Next
    INDEX
    Explanations

    Jungle Scout, Amazon, Helium 10

    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
    TEGER
    0.37
     H
    0.36
     Cote
    0.36
    h
    0.36
    hara
    0.36
     an
    0.35
     Moral
    0.35
     Haram
    0.35
     Hegel
    0.35
     all
    0.35
    POSITIVE LOGITS
    ුවේ
    0.32
    ávy
    0.31
     टाइ
    0.31
    账
    0.31
    वियस
    0.30
     швидко
    0.30
    蝕
    0.30
    și
    0.30
     nho
    0.30
    瓷
    0.30
    Activations Density 0.002%

    No Known Activations