© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 124935
    Prev
    Next
    INDEX
    Explanations

    CAPTCHA solving

    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_3_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
    ดัง
    0.70
    Iy
    0.69
     promulg
    0.68
     gamm
    0.66
    alang
    0.65
    a
    0.65
     cousin
    0.63
     tibia
    0.63
     dati
    0.63
     figurine
    0.62
    POSITIVE LOGITS
    𝚣
    0.97
     to
    0.86
    𝘇
    0.83
    ات
    0.82
    ش
    0.79
    то
    0.79
    𝚘
    0.75
    𝚟
    0.75
    רי
    0.74
    وا
    0.73
    Activations Density 0.000%

    No Known Activations