© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 85889
    Prev
    Next
    INDEX
    Explanations

    high-level overview

    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_23_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
     autoWatch
    0.48
    পাড়া
    0.41
     Prag
    0.38
     популя
    0.37
     মত
    0.36
    𝙛
    0.36
    ⒋
    0.36
    𝘼
    0.36
    ्त
    0.36
     metagen
    0.35
    POSITIVE LOGITS
     alone
    0.48
    alone
    0.46
    เท่านั้น
    0.45
     thôi
    0.44
    only
    0.41
    のみ
    0.39
     だけ
    0.39
    만을
    0.39
    isms
    0.39
     desn
    0.37
    Activations Density 0.082%

    No Known Activations