© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 50767
    Prev
    Next
    INDEX
    Explanations

    routes between locations

    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_30_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
     많
    0.38
     فهي
    0.37
     괜
    0.37
     כן
    0.37
     ವಿರು
    0.35
     thật
    0.35
    แต
    0.35
    atici
    0.34
    อื่นๆ
    0.34
    indah
    0.34
    POSITIVE LOGITS
     controversy
    0.38
    ၟ
    0.37
    वाधिकार
    0.35
     agitation
    0.35
     shocking
    0.33
     hinged
    0.33
     Garfield
    0.33
    Fat
    0.33
     archaeological
    0.33
     രാജ
    0.33
    Activations Density 0.002%

    No Known Activations