© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 214577
    Prev
    Next
    INDEX
    Explanations

    movement

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_47_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
     pesso
    0.38
    邝
    0.38
    )}-
    0.38
    বান্ধ
    0.38
     ច
    0.37
     singkat
    0.37
     empat
    0.37
     sè
    0.37
    📀
    0.36
    Gioco
    0.36
    POSITIVE LOGITS
    Model
    0.44
    MODEL
    0.40
    move
    0.39
    cris
    0.39
    PTR
    0.37
     Model
    0.36
    =","><
    0.36
    PILE
    0.36
    лети
    0.35
    heap
    0.35
    Activations Density 0.005%

    No Known Activations