© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 5799
    Prev
    Next
    INDEX
    Explanations

    cobol, Jim Crow, MATLAB, martrix

    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_39_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
     cant
    0.39
    بیر
    0.39
    ങ്ങ്
    0.39
    umbres
    0.38
     Chiến
    0.38
    湫
    0.38
    かね
    0.37
    崆
    0.36
    ලි
    0.36
    бир
    0.36
    POSITIVE LOGITS
     enrolment
    0.39
     Robotic
    0.37
    """"
    0.36
     enrollment
    0.35
     pilot
    0.35
    마다
    0.35
     部
    0.34
    ולוג
    0.34
    🐒
    0.34
    鬚
    0.34
    Activations Density 0.058%

    No Known Activations