© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 141887
    Prev
    Next
    INDEX
    Explanations

    neuroectodermal, mesoderm, endoderm

    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_12_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
    lj
    0.62
    da
    0.60
    äude
    0.57
    r
    0.57
    l
    0.56
    FBSDKGraph
    0.55
    der
    0.54
     বসবাস
    0.53
    ktiv
    0.53
    professional
    0.52
    POSITIVE LOGITS
     balón
    0.62
     micrófono
    0.57
     lumps
    0.55
     ordinarily
    0.54
     caído
    0.54
     mirando
    0.53
     WOULD
    0.53
     quotients
    0.52
    筈
    0.51
     weren
    0.50
    Activations Density 0.000%

    No Known Activations