© 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. 8586
    Prev
    Next
    INDEX
    Explanations

    greatest achievements

    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
     fraudulently
    2.91
    𝒾
    2.86
    ীয়
    2.77
    ка
    2.75
    те
    2.74
    ik
    2.71
    jumpa
    2.68
    Boe
    2.65
    cgColor
    2.61
    یه
    2.60
    POSITIVE LOGITS
    брита
    3.03
     apes
    2.80
     brit
    2.79
     strides
    2.76
     rasgos
    2.75
     fanfare
    2.65
    с
    2.64
    resposta
    2.61
    ف
    2.59
    pumpkin
    2.58
    Activations Density 0.001%

    No Known Activations