© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 165413
    Prev
    Next
    INDEX
    Explanations

    Donbas

    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_34_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
    щи
    0.41
    IAS
    0.40
    仮想
    0.40
    หลด
    0.39
    փ
    0.38
    rivial
    0.37
     கால
    0.37
    estream
    0.37
     Orphan
    0.37
    ordinator
    0.36
    POSITIVE LOGITS
     secolo
    0.38
     biore
    0.37
     siglos
    0.37
     katal
    0.36
     liu
    0.36
     century
    0.36
     برش
    0.36
    சாக
    0.36
    century
    0.36
     액
    0.36
    Activations Density 0.002%

    No Known Activations