© 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. 171546
    Prev
    Next
    INDEX
    Explanations

    price ($)

    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
     tableware
    0.46
     ша
    0.42
    陳
    0.41
    עד
    0.40
    urnama
    0.39
     cholinergic
    0.39
    _
    0.39
     associ
    0.38
    ukiyoe
    0.38
     monographs
    0.38
    POSITIVE LOGITS
    並
    0.49
     bởi
    0.48
     Oakland
    0.44
    Environmental
    0.44
     translator
    0.43
     surplus
    0.42
    雪
    0.42
     ഷോ
    0.41
    ரிய
    0.40
    ाइन
    0.40
    Activations Density 0.000%

    No Known Activations