© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 210838
    Prev
    Next
    INDEX
    Explanations

    tipping and service charges

    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_20_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
     剤
    0.45
    ダ
    0.44
     Dots
    0.43
    id
    0.43
    tä
    0.43
     omdat
    0.42
     Nxc
    0.42
     []:
    0.41
    strom
    0.41
     njega
    0.40
    POSITIVE LOGITS
    Educational
    0.48
    Pclass
    0.44
    Satisfaction
    0.44
     levelled
    0.43
    Visiting
    0.43
    妘
    0.43
    Rewards
    0.42
    According
    0.41
    Estimate
    0.40
    颇
    0.40
    Activations Density 0.000%

    No Known Activations