© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 25790
    Prev
    Next
    INDEX
    Explanations

    Australia, Outback, deserts, grasslands

    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_10_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
    ?”.
    0.53
    mét
    0.48
    忝
    0.48
    gaxModule
    0.48
    <unused2019>
    0.47
     témoign
    0.45
     fühlen
    0.45
    änglich
    0.44
    ploid
    0.44
    .`);
    0.44
    POSITIVE LOGITS
     deserts
    0.55
    na
    0.54
    Na
    0.52
    на
    0.51
    Cars
    0.50
    Australia
    0.50
     Outback
    0.50
    נה
    0.49
    ना
    0.48
    Star
    0.48
    Activations Density 0.008%

    No Known Activations