© 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. 126991
    Prev
    Next
    INDEX
    Explanations

    file not found error handling

    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
     типо
    0.44
     جیک
    0.39
     some
    0.38
    eteries
    0.38
     QUALITY
    0.38
     型
    0.37
     Len
    0.37
     NAB
    0.37
     niektor
    0.37
     Leon
    0.37
    POSITIVE LOGITS
    carpet
    0.46
    Guide
    0.45
    guide
    0.43
    guides
    0.42
     guide
    0.39
    Casa
    0.39
     unzip
    0.38
    ➥
    0.38
    crash
    0.37
     Guide
    0.37
    Activations Density 0.001%

    No Known Activations