© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 166279
    Prev
    Next
    INDEX
    Explanations

    threaten to

    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
    thisComponent
    0.39
     مباش
    0.39
    を果た
    0.39
     watert
    0.38
     নিরাপদ
    0.37
    conoc
    0.36
    嗇
    0.36
     Yose
    0.36
     besitzt
    0.36
    ীরে
    0.36
    POSITIVE LOGITS
     reverting
    0.42
     Venus
    0.37
    лава
    0.35
    ᶤ
    0.35
     Pode
    0.35
    ເວ
    0.34
     geared
    0.33
     đáy
    0.33
    gsub
    0.33
     Sten
    0.33
    Activations Density 0.001%

    No Known Activations