© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 207461
    Prev
    Next
    INDEX
    Explanations

    fluid or contents

    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
    ActionResult
    0.20
    नुसार
    0.19
    AllResult
    0.19
     \%)$
    0.19
    OID
    0.18
    후
    0.18
    ጁ
    0.18
     ->
    0.18
    กี
    0.18
    📄
    0.18
    POSITIVE LOGITS
    yelination
    0.18
    стрее
    0.17
    <unused47>
    0.16
    रीबन
    0.16
    مارسة
    0.16
    పర్
    0.16
    alma
    0.16
     Dist
    0.16
     Virology
    0.16
    τεί
    0.16
    Activations Density 0.002%

    No Known Activations