© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 49761
    Prev
    Next
    INDEX
    Explanations

    permits and licenses required

    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_31_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
     genetically
    0.27
    ElementException
    0.26
    кать
    0.26
    餮
    0.26
    غن
    0.25
    örder
    0.25
     calcareous
    0.25
     Californians
    0.25
    మిక
    0.24
    聒
    0.24
    POSITIVE LOGITS
    aboration
    0.30
    acionales
    0.27
    ADMIN
    0.27
    cosim
    0.27
     visto
    0.26
    萱
    0.26
     visible
    0.26
     raising
    0.26
     prot
    0.26
     javascript
    0.26
    Activations Density 0.007%

    No Known Activations