© 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-3-4B-IT
    3. 5-GEMMASCOPE-2-TRANSCODER-262K
    4. 3350
    Prev
    Next
    INDEX
    Explanations

    any type annotation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_5_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
     Некоторые
    1.25
     $(<
    1.20
    beige
    1.10
    uction
    1.09
     그런데
    1.09
     bagian
    1.08
    та
    1.07
    みる
    1.06
    みると
    1.06
    aient
    1.06
    POSITIVE LOGITS
    <bos>
    1.23
    כת
    1.13
    tic
    1.07
     expect
    1.05
     কেশ
    1.02
    Alk
    1.00
    
    0.97
    rick
    0.97
    जनक
    0.96
     intenta
    0.95
    Activations Density 0.004%

    No Known Activations