© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 207642
    Prev
    Next
    INDEX
    Explanations

    resources, conversation, the

    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_25_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
    িলম্বে
    0.36
    kusen
    0.35
    谍
    0.34
     ລັບ
    0.34
    ოდა
    0.33
    itôt
    0.33
    圴
    0.32
    łaś
    0.31
     নু
    0.31
     половине
    0.31
    POSITIVE LOGITS
    Charts
    0.41
     UNC
    0.38
     техники
    0.38
     facial
    0.37
    咬
    0.36
     سٹ
    0.36
    UNC
    0.35
     shrug
    0.35
     U
    0.34
     gcc
    0.34
    Activations Density 0.019%

    No Known Activations