© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 201646
    Prev
    Next
    INDEX
    Explanations

    pairs and angle brackets

    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_37_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
     Fake
    0.38
    asone
    0.35
    🎁
    0.34
     fake
    0.34
     congenital
    0.34
    ສົ່ງ
    0.34
    子が
    0.34
    Lore
    0.33
    fake
    0.33
     порядке
    0.32
    POSITIVE LOGITS
    僻
    0.39
     prirod
    0.38
     pointers
    0.37
    ච
    0.37
     DUR
    0.36
    trimenti
    0.36
     నియ
    0.36
    چر
    0.36
     ressent
    0.35
    achment
    0.35
    Activations Density 0.000%

    No Known Activations