© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 7454
    Prev
    Next
    INDEX
    Explanations

    color : image

    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_40_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
     Monty
    0.43
    तील
    0.40
     yogurt
    0.38
    慾
    0.38
    skap
    0.37
    MONT
    0.37
     şek
    0.37
     MONT
    0.37
    íso
    0.37
    喻
    0.36
    POSITIVE LOGITS
    ドウ
    0.37
     نست
    0.36
    하려고
    0.35
     가
    0.34
    οντας
    0.33
     Ond
    0.33
    rowadz
    0.33
    rile
    0.33
    guardian
    0.33
    oxylated
    0.33
    Activations Density 0.014%

    No Known Activations