© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 7888
    Prev
    Next
    INDEX
    Explanations

    multiple times higher

    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_3_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
    جة
    1.57
    }$:
    1.56
     trem
    1.41
     sveta
    1.40
     rask
    1.40
    í
    1.38
    靂
    1.37
    ItemsSource
    1.37
    ุล
    1.37
     complic
    1.36
    POSITIVE LOGITS
    arjo
    1.67
    ונה
    1.51
    clide
    1.49
    eced
    1.48
    eel
    1.46
    其他
    1.45
    eket
    1.44
    ே
    1.43
    ことです
    1.43
    planned
    1.41
    Activations Density 0.077%

    No Known Activations