© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 206461
    Prev
    Next
    INDEX
    Explanations

    batch or shell scripts

    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_20_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
    ሆ
    0.47
    T
    0.45
    டி
    0.44
    Prz
    0.43
     wreaths
    0.43
    Verb
    0.41
    oths
    0.40
    限定
    0.40
    configuring
    0.40
    தியான
    0.39
    POSITIVE LOGITS
     інте
    0.44
     Langer
    0.42
    ⱱ
    0.41
     ANO
    0.41
     Lebensmittel
    0.40
    neapolis
    0.39
     Karol
    0.39
    鎗
    0.39
     Waterproof
    0.38
     πι
    0.38
    Activations Density 0.000%

    No Known Activations