© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 164676
    Prev
    Next
    INDEX
    Explanations

    window features

    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
     Facilities
    0.45
     facilities
    0.41
     crying
    0.40
     cellar
    0.39
    Facilities
    0.38
     cez
    0.38
    ʎ
    0.38
    tuned
    0.38
    toni
    0.38
     Wail
    0.37
    POSITIVE LOGITS
    সই
    0.39
     সড়কের
    0.37
    帶來
    0.37
    អា
    0.36
     सड़क
    0.36
    腎
    0.36
     stake
    0.35
    ська
    0.35
    ROAD
    0.34
    JScripts
    0.34
    Activations Density 0.001%

    No Known Activations