© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 205922
    Prev
    Next
    INDEX
    Explanations

    API keys and tokens

    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_25_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
    orylation
    0.41
     necessitated
    0.40
    γκεκρι
    0.39
     exacerbated
    0.38
    ),]
    0.37
     frowned
    0.36
     росій
    0.36
     Moya
    0.35
     fok
    0.35
     oksid
    0.35
    POSITIVE LOGITS
     גם
    0.36
     genus
    0.35
     לע
    0.34
     animals
    0.34
    बाइक
    0.34
     graph
    0.33
    塁
    0.33
     bike
    0.33
     composite
    0.32
     baba
    0.32
    Activations Density 0.002%

    No Known Activations