© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 18334
    Prev
    Next
    INDEX
    Explanations

    XML, SOAP, multipart, pivot

    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_15_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
    K
    0.60
    V
    0.58
    F
    0.54
    ಬ
    0.53
    ische
    0.51
     பரபர
    0.51
    U
    0.50
     sa
    0.50
     zeigt
    0.47
     Tertiary
    0.47
    POSITIVE LOGITS
     selectInput
    0.52
    드의
    0.48
     oftent
    0.47
    webserv
    0.47
    хин
    0.47
    dlj
    0.46
    hx
    0.46
    продук
    0.46
    ****/
    0.46
    Listening
    0.46
    Activations Density 0.053%

    No Known Activations