© 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. 8356
    Prev
    Next
    INDEX
    Explanations

    directly against

    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
    注意的是
    1.91
    ش
    1.87
     jaw
    1.73
     jaws
    1.63
    за
    1.61
     imao
    1.59
    স্টার
    1.59
     efectu
    1.58
     receivable
    1.57
     llegue
    1.57
    POSITIVE LOGITS
    er
    2.59
    ehr
    2.01
    NSLog
    2.00
    e
    1.96
    কিছু
    1.96
    ى
    1.91
     Bxg
    1.88
    udrait
    1.87
     Rxf
    1.86
    ার
    1.85
    Activations Density 0.049%

    No Known Activations