© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 49616
    Prev
    Next
    INDEX
    Explanations

    memes and expressions

    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_55_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
    ​
    0.45
    -​
    0.43
    .​
    0.42
    Attenuation
    0.42
    ‐
    0.40
    ​)
    0.38
    ⁤
    0.37
     craters
    0.37
     applicability
    0.37
     lign
    0.36
    POSITIVE LOGITS
     मिमी
    0.41
    <0xD0>
    0.40
     intern
    0.39
     Friend
    0.39
     કર્યા
    0.39
     introvert
    0.38
     сист
    0.38
     inventor
    0.38
     Influ
    0.38
    мили
    0.38
    Activations Density 0.009%

    No Known Activations