© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 126915
    Prev
    Next
    INDEX
    Explanations

    memory management

    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_37_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
    分配
    0.48
    USB
    0.44
     allocator
    0.42
    릴
    0.41
     behave
    0.40
     lastName
    0.38
    सन्
    0.38
    turtle
    0.37
    닭
    0.37
     amplifier
    0.36
    POSITIVE LOGITS
    нную
    0.45
     blancos
    0.42
    mec
    0.38
     Nig
    0.38
     pressures
    0.37
    relli
    0.37
     силу
    0.37
     stel
    0.37
    джу
    0.36
     nig
    0.36
    Activations Density 0.001%

    No Known Activations