© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 12-GEMMASCOPE-2-TRANSCODER-262K
    4. 201249
    Prev
    Next
    INDEX
    Explanations

    keypoint detection

    np_acts-logits-general · gemini-2.5-flash-lite

    feature points

    np_max-act-logits · gemini-2.5-flash-liteTriggered by @enricobottazzi

    terms related to image or data features.

    oai_token-act-pair · gemini-2.5-flash-liteTriggered by @enricobottazzi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_12_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
    Ut
    0.17
    साठी
    0.16
    Aer
    0.16
    Gut
    0.16
    Repair
    0.16
    怵
    0.16
    Gmail
    0.16
    OLA
    0.16
    ोग्राफी
    0.16
     urna
    0.15
    POSITIVE LOGITS
     সন্দ
    0.15
    ↵
    0.14
     यावेळी
    0.14
    <0x8E>
    0.14
     величе
    0.13
     acquitted
    0.13
     criminally
    0.13
     Malcolm
    0.13
     Стра
    0.13
     vencedor
    0.13
    Activations Density 0.003%

    No Known Activations