© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 45506
    Prev
    Next
    INDEX
    Explanations

    handling POST REQUEST

    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_22_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
    Toolset
    0.44
    DAN
    0.42
    DC
    0.42
     DSL
    0.41
    BGR
    0.40
    म
    0.39
    бли
    0.39
     Tshirt
    0.39
    <0xE2>
    0.39
    Ethan
    0.39
    POSITIVE LOGITS
     probleem
    0.46
     problema
    0.46
     bū
    0.45
     መጨ
    0.44
     není
    0.44
     کردہ
    0.42
     niemand
    0.41
     misschien
    0.40
     kwaliteit
    0.39
    簑
    0.39
    Activations Density 0.000%

    No Known Activations