© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 197114
    Prev
    Next
    INDEX
    Explanations

    masking or duct tape

    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_15_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
    ম
    0.52
    म
    0.51
     Curie
    0.50
    बता
    0.50
    емым
    0.50
    任何
    0.49
     neuropathy
    0.49
     Gull
    0.48
    ងឺ
    0.48
    つけて
    0.48
    POSITIVE LOGITS
    }:=
    0.60
    oop
    0.55
    istem
    0.52
     Kingdoms
    0.51
    awal
    0.51
    il
    0.50
    rine
    0.49
    idol
    0.49
     친
    0.48
    isn
    0.48
    Activations Density 0.000%

    No Known Activations