© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 259565
    Prev
    Next
    INDEX
    Explanations

    album tracks song

    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
    +,
    0.40
     Согласно
    0.36
     สิ่ง
    0.35
     ಪ್ರಮಾಣ
    0.35
     द्वारा
    0.35
     Citrus
    0.35
     Plaza
    0.34
     circles
    0.34
    adari
    0.34
     inwards
    0.33
    POSITIVE LOGITS
    ান্তরে
    0.41
    kingen
    0.37
    Charset
    0.36
    贰章
    0.36
    questao
    0.35
    攽
    0.35
    aciju
    0.35
    liko
    0.34
    잌
    0.34
     methanol
    0.34
    Activations Density 0.002%

    No Known Activations