© 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. 213844
    Prev
    Next
    INDEX
    Explanations

    Apple products

    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
    定的
    0.37
    极
    0.37
    𝑁
    0.37
     ሥ
    0.37
     شر
    0.37
    ()));
    0.37
    pocket
    0.37
    N
    0.35
     Ty
    0.34
    гне
    0.34
    POSITIVE LOGITS
     cosecha
    0.40
     specimen
    0.40
    cala
    0.38
    璺
    0.38
     venga
    0.37
     भुजा
    0.36
    cmml
    0.36
    ouche
    0.36
     st
    0.35
     ст
    0.35
    Activations Density 0.001%

    No Known Activations