© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 195421
    Prev
    Next
    INDEX
    Explanations

    breakdown, uses, and variations

    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_27_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
     ऑक्सीजन
    0.32
    ക്കുറിച്ച്
    0.32
     प्रशासनिक
    0.31
     চ্যানেল
    0.31
    竴
    0.31
     respite
    0.30
     صف
    0.30
     appropriately
    0.30
     scrolls
    0.30
     журнала
    0.30
    POSITIVE LOGITS
    ೇವಿನ
    0.38
    aturan
    0.36
    stern
    0.36
    Stern
    0.35
    íf
    0.35
     temu
    0.35
    enta
    0.34
     Evam
    0.33
     \\\
    0.33
    )}_{\
    0.33
    Activations Density 0.026%

    No Known Activations