© 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. 6600
    Prev
    Next
    INDEX
    Explanations

    high-level

    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
    اء
    0.87
    ian
    0.79
    о
    0.76
    ка
    0.76
    ена
    0.71
    на
    0.70
    ן
    0.69
    {})
    0.67
    al
    0.66
    radas
    0.65
    POSITIVE LOGITS
     muut
    0.71
     tuh
    0.67
     бушлай
    0.66
    fromDate
    0.64
    дуу
    0.62
     CodeableConcept
    0.62
    father
    0.60
    에
    0.59
     handleSubmit
    0.59
     viciss
    0.59
    Activations Density 0.056%

    No Known Activations