© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 132202
    Prev
    Next
    INDEX
    Explanations

    unwanted

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    アイデア
    0.48
    Unt
    0.44
     ideas
    0.43
    Ideas
    0.43
     Ideas
    0.41
     Outline
    0.40
    妑
    0.39
     Maur
    0.37
    UTS
    0.37
    運
    0.37
    POSITIVE LOGITS
     poco
    0.45
     peu
    0.42
    icamente
    0.40
     buen
    0.39
    exceptional
    0.38
    oppable
    0.38
    forgettable
    0.37
    iquement
    0.37
    readable
    0.37
    proven
    0.37
    Activations Density 0.004%

    No Known Activations