© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 197993
    Prev
    Next
    INDEX
    Explanations

    words indicating addition or augmentation

    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_15_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
     بالك
    0.21
     ما
    0.19
    ırl
    0.18
     Oed
    0.18
     proteger
    0.17
     స
    0.17
    孔
    0.17
     يح
    0.17
    ま
    0.17
     وم
    0.17
    POSITIVE LOGITS
    യാ
    0.18
    قدم
    0.18
    اید
    0.18
    ed
    0.17
    ables
    0.17
    संस्करण
    0.16
    素敵
    0.16
    al
    0.16
    dimension
    0.16
    ാൻഡ്
    0.15
    Activations Density 0.009%

    No Known Activations