© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 241104
    Prev
    Next
    INDEX
    Explanations

    console

    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_25_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
    ja
    0.44
    au
    0.42
    ou
    0.41
     )
    0.40
     Net
    0.40
    ama
    0.39
     Large
    0.39
    ya
    0.38
     Are
    0.38
    idlo
    0.38
    POSITIVE LOGITS
    ಿತಿ
    0.42
    ፡፡
    0.41
    ༧
    0.41
    用意
    0.40
    ContactBundle
    0.40
    𒌝
    0.39
     ناخذ
    0.39
    ArrowToggle
    0.38
     разработан
    0.38
     Colombe
    0.38
    Activations Density 0.000%

    No Known Activations