© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 16569
    Prev
    Next
    INDEX
    Explanations

    along the

    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_40_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
    ക്കെ
    0.39
    ョ
    0.39
     tow
    0.38
    যোগী
    0.36
     дода
    0.36
    ോളം
    0.36
    徑
    0.36
     follow
    0.35
    complement
    0.35
    icho
    0.35
    POSITIVE LOGITS
    स्तिष्क
    0.40
    ภาษ
    0.40
     क्वे
    0.39
     lakes
    0.38
    剔
    0.38
    Containers
    0.38
     четырех
    0.37
    Ⲟ
    0.37
    AKER
    0.36
     uzav
    0.36
    Activations Density 0.007%

    No Known Activations