© 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. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 210602
    Prev
    Next
    INDEX
    Explanations

    currently at

    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_19_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
     Prinzip
    0.49
    tay
    0.49
     واپ
    0.48
    го
    0.46
    tos
    0.46
    렸
    0.46
    doctors
    0.45
    ג
    0.44
    los
    0.44
    OHAMA
    0.44
    POSITIVE LOGITS
     Zone
    0.44
    เจอ
    0.43
    単
    0.43
     पड़ने
    0.42
     mojo
    0.42
     offering
    0.41
    เป็น
    0.40
     retreats
    0.40
    涷
    0.40
     hanno
    0.40
    Activations Density 0.000%

    No Known Activations