© 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. 3161
    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
    fully
    2.56
    নি
    2.50
    ে
    2.41
    zeitig
    2.33
    e
    2.30
     schematically
    2.20
    și
    2.16
    tanto
    2.13
    ש
    2.09
    স
    2.09
    POSITIVE LOGITS
    는
    2.39
    ﻱ
    2.37
    ا
    2.37
    ﺇ
    2.35
    فة
    2.24
    я
    2.19
     courtship
    2.19
     Daughters
    2.16
    ايا
    2.15
     riscos
    2.13
    Activations Density 0.023%

    No Known Activations