© 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-3-4B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 245771
    Prev
    Next
    INDEX
    Explanations

    employment and related concepts

    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_11_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
     নাব
    0.40
    थरूम
    0.40
     raft
    0.38
    திக
    0.38
     dominates
    0.36
    });
    0.36
    '>");
    0.36
     obviously
    0.36
    (`#
    0.35
    okol
    0.35
    POSITIVE LOGITS
    很少
    0.48
     LPS
    0.46
     రోజు
    0.44
     PCE
    0.44
     VND
    0.43
     Thời
    0.43
    健身
    0.42
     fiori
    0.42
    Reset
    0.42
     Bite
    0.42
    Activations Density 0.001%

    No Known Activations