© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 6846
    Prev
    Next
    INDEX
    Explanations

    instrumental break

    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
    в
    2.31
     encouraging
    2.14
    Ƭ
    2.12
    BJP
    2.11
     आक
    2.01
     ramus
    1.98
    šie
    1.97
    чего
    1.96
     baut
    1.96
     firmly
    1.94
    POSITIVE LOGITS
    л
    2.51
    tips
    2.12
    м
    2.02
    ยนต์
    1.93
    kits
    1.91
    ্লাহ
    1.91
    ্যা
    1.87
    z
    1.83
     sast
    1.81
    ು
    1.80
    Activations Density 0.073%

    No Known Activations