© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 167905
    Prev
    Next
    INDEX
    Explanations

    URLs and addresses

    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_34_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
     Derr
    0.42
     lb
    0.41
    ჩ
    0.38
     සඳහා
    0.38
    চন্দ্র
    0.37
     reta
    0.37
     splice
    0.37
     McMahon
    0.37
     cilind
    0.36
     half
    0.36
    POSITIVE LOGITS
    ipping
    0.39
    <0x0F>
    0.37
     formado
    0.37
    バシー
    0.37
    ips
    0.37
    𝑨
    0.37
    渗
    0.36
    祅
    0.36
    𝙇
    0.36
     ሂደት
    0.35
    Activations Density 0.002%

    No Known Activations