© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 116021
    Prev
    Next
    INDEX
    Explanations

    1 | or 2 |

    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
    addi
    0.47
    を除く
    0.41
    \{{}\
    0.37
    cine
    0.36
     বিকা
    0.36
    についても
    0.36
    副本
    0.36
    सन
    0.36
    眽
    0.36
     производ
    0.36
    POSITIVE LOGITS
     catalase
    0.41
     pil
    0.41
     peper
    0.41
     PIL
    0.40
     bicolor
    0.39
     helmet
    0.39
     securely
    0.38
    Pil
    0.38
     стрелецкой
    0.38
     glucocortic
    0.37
    Activations Density 0.001%

    No Known Activations