© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 151033
    Prev
    Next
    INDEX
    Explanations

    `cdk bootstrap`

    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_23_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
    נג
    0.48
    Odd
    0.48
    Deal
    0.44
     লন্ডন
    0.44
    芾
    0.44
    Invite
    0.43
     ηλεκ
    0.43
    Size
    0.42
    Right
    0.42
    উট
    0.41
    POSITIVE LOGITS
    邨
    0.48
    amar
    0.46
     Pullman
    0.45
     s
    0.44
    ef
    0.44
    akn
    0.44
    ana
    0.43
     Faz
    0.43
     chronic
    0.42
     playwright
    0.42
    Activations Density 0.000%

    No Known Activations