© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 9070
    Prev
    Next
    INDEX
    Explanations

    ` `chain.run`

    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_40_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
    宣告
    0.44
     &=\
    0.40
    }=[
    0.40
    seller
    0.39
     தொ
    0.38
    痞
    0.38
     مبس
    0.37
    ʃ
    0.37
    ))[
    0.37
     concave
    0.37
    POSITIVE LOGITS
    राउंड
    0.41
     McK
    0.40
     runtime
    0.38
    cutoff
    0.37
     Walden
    0.37
    บู
    0.37
    ленных
    0.36
    ል።
    0.36
     tri
    0.36
     Pana
    0.36
    Activations Density 0.001%

    No Known Activations