© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 164160
    Prev
    Next
    INDEX
    Explanations

    looking for alternatives

    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_31_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
     ønsk
    0.38
     चाहें
    0.36
    ູ
    0.36
    想要
    0.35
     Catalyst
    0.35
     evolved
    0.35
     catalyst
    0.35
    ካል
    0.35
     Celia
    0.34
     accelerates
    0.34
    POSITIVE LOGITS
     Bởi
    0.44
     Porque
    0.42
    मेर
    0.41
    Editing
    0.41
     थरूर
    0.39
    ╿
    0.39
    impulan
    0.39
    urusan
    0.39
     svojoj
    0.38
    acheter
    0.38
    Activations Density 0.002%

    No Known Activations