© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 144604
    Prev
    Next
    INDEX
    Explanations

    applying a pattern

    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_0_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
     indole
    0.53
     che
    0.48
    as
    0.48
    ľov
    0.46
    ﻒ
    0.46
     settembre
    0.46
     indol
    0.46
     acc
    0.45
     categor
    0.45
     pantalla
    0.45
    POSITIVE LOGITS
    Под
    0.49
    assertEqual
    0.46
    万元
    0.45
    Rw
    0.45
    euler
    0.45
    rq
    0.45
    Castle
    0.45
     ደቂ
    0.45
    Д
    0.44
    лт
    0.44
    Activations Density 0.000%

    No Known Activations