© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 207337
    Prev
    Next
    INDEX
    Explanations

    make it a habit, game, or regular thing

    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_20_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
    ky
    0.45
    autes
    0.44
    chid
    0.44
     wondrous
    0.42
    🌩
    0.41
    роид
    0.39
    othiaz
    0.39
    CLOUD
    0.39
     ঘটেছে
    0.38
     (€
    0.38
    POSITIVE LOGITS
    任何
    0.46
     any
    0.42
    ص
    0.42
     ona
    0.40
     defaulting
    0.40
     본
    0.39
    閑
    0.39
     pig
    0.39
    staticmethod
    0.39
    Lemma
    0.39
    Activations Density 0.001%

    No Known Activations