© 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. 7287
    Prev
    Next
    INDEX
    Explanations

    Adam optimizer

    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
    
    3.06
    rä
    2.86
     regard
    2.61
    ৬
    2.61
    \%,
    2.44
    ل
    2.37
     положение
    2.32
     spoken
    2.31
     Stewardship
    2.22
    <%=
    2.21
    POSITIVE LOGITS
    ه
    3.25
    ло
    3.02
    ভাবে
    2.80
     фами
    2.67
     junit
    2.59
     keren
    2.55
    en
    2.54
    まま
    2.51
    ly
    2.51
    스를
    2.49
    Activations Density 0.019%

    No Known Activations