© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 42199
    Prev
    Next
    INDEX
    Explanations

    areas like

    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_22_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
     বিষয়টি
    0.48
     idP
    0.47
     நைட்
    0.47
     démarche
    0.45
    ড্রিম
    0.45
    _'+
    0.44
    као
    0.44
    クロマト
    0.44
    銈
    0.43
     செய்வது
    0.43
    POSITIVE LOGITS
     the
    0.42
    <0xE3>
    0.40
    在
    0.40
    рту
    0.39
    ↵
    0.39
    ）。
    0.39
     benefits
    0.38
    带
    0.38
    and
    0.38
    the
    0.38
    Activations Density 0.008%

    No Known Activations