© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 53595
    Prev
    Next
    INDEX
    Explanations

    sources familiar with

    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_30_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
     আভ্যন্তরীণ
    0.57
     rumoured
    0.52
     Ayn
    0.45
     sanitary
    0.39
    !!");
    0.39
    circulation
    0.38
     rumored
    0.37
     lawsuit
    0.36
    ząt
    0.36
     اكس
    0.35
    POSITIVE LOGITS
    сторон
    0.37
    lores
    0.34
     diente
    0.33
    拘
    0.33
     putty
    0.33
     സഞ്ച
    0.32
     לנו
    0.32
     আরোপ
    0.32
    理念
    0.32
    ან
    0.32
    Activations Density 0.000%

    No Known Activations