© 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. 206915
    Prev
    Next
    INDEX
    Explanations

    tasted like [material/state]

    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
     upaya
    0.47
     ascension
    0.47
     និង
    0.46
    ’?
    0.46
    '?
    0.45
     যদি
    0.45
     맨
    0.44
     ແລະ
    0.44
     και
    0.43
     situatie
    0.43
    POSITIVE LOGITS
    ynchronous
    0.39
    キシ
    0.39
    ]%
    0.38
    こだ
    0.38
    infty
    0.37
    Ns
    0.37
    Lowercase
    0.37
    五
    0.37
    xk
    0.37
    Uppercase
    0.36
    Activations Density 0.006%

    No Known Activations