© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 6442
    Prev
    Next
    INDEX
    Explanations

    InitializeComponent()

    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_39_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
     moh
    0.41
     omkring
    0.36
    減少
    0.36
    ኙ
    0.36
    পিড
    0.35
     bas
    0.35
     পৃষ্ঠপোষ
    0.34
    侬
    0.34
     рецен
    0.34
     peringkat
    0.34
    POSITIVE LOGITS
     അന്ത
    0.41
     necessária
    0.37
    ডার
    0.37
     hev
    0.36
     แชร์
    0.36
     useful
    0.35
    зова
    0.35
     prejudicial
    0.35
    Field
    0.34
     Required
    0.34
    Activations Density 0.000%

    No Known Activations