© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 66896
    Prev
    Next
    INDEX
    Explanations

    public transport and infrastructure

    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_41_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
    私
    0.42
     Private
    0.40
    Vir
    0.39
    向き
    0.38
    ωσ
    0.37
     PRIVATE
    0.37
    Private
    0.36
    enie
    0.36
    私人
    0.36
    ās
    0.35
    POSITIVE LOGITS
    contracts
    0.39
    Contracts
    0.38
    韌
    0.36
    attrs
    0.36
    റു
    0.36
    韧
    0.36
     Atra
    0.35
     neu
    0.35
     término
    0.35
     Ruff
    0.35
    Activations Density 0.005%

    No Known Activations