© 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
    2. Gemma-3-27B-IT
    3. 39-GEMMASCOPE-2-TRANSCODER-262K
    4. 3974
    Prev
    Next
    INDEX
    Explanations

    libraries and technologies

    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_39_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
    insa
    0.25
    incy
    0.22
    ampo
    0.22
    ogenen
    0.21
    aisse
    0.20
    ulkner
    0.20
    癥
    0.20
    ids
    0.20
    ombi
    0.20
    anon
    0.20
    POSITIVE LOGITS
    Lib
    0.20
    ->"
    0.20
    Shot
    0.19
     reproduct
    0.19
    พาะ
    0.19
     Przy
    0.19
    隐含规则
    0.18
     zupeł
    0.18
    ittest
    0.18
    အတွက်
    0.18
    Activations Density 0.456%

    No Known Activations