© 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. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 3324
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_2_width_16k_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
     CHLOR
    2.72
     femen
    2.69
     FIXED
    2.52
     пройдет
    2.47
    copter
    2.46
    cyst
    2.44
     randon
    2.43
    d
    2.41
    cyt
    2.40
    cY
    2.38
    POSITIVE LOGITS
    an
    3.49
    neath
    2.35
    regardless
    2.23
    is
    2.23
    side
    2.18
    AN
    2.17
    ાગ
    2.14
    ق
    2.13
    на
    2.12
    𝑒
    2.11
    Activations Density 0.004%

    No Known Activations