© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 121091
    Prev
    Next
    INDEX
    Explanations

    being on a paid plan

    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_38_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
    𝖓
    0.44
     trusts
    0.39
    ()'
    0.39
    犃
    0.39
     цене
    0.38
     परंतु
    0.38
    contentInset
    0.38
     NVIC
    0.38
    恼
    0.37
     ペンダント
    0.37
    POSITIVE LOGITS
    Extra
    0.41
    Bud
    0.40
     extra
    0.40
    达
    0.39
     chalk
    0.39
     cubed
    0.38
     hoà
    0.38
    extra
    0.37
     “
    0.37
     cus
    0.36
    Activations Density 0.000%

    No Known Activations