© 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. 2752
    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
    𝐚
    2.48
     abr
    2.37
    <%=
    2.35
     glory
    2.33
    𝒓
    2.22
    leistungen
    2.18
    aneous
    2.13
    𝒊
    2.12
     invariants
    2.11
     capita
    2.11
    POSITIVE LOGITS
    ्स
    2.66
    માં
    2.50
    થી
    2.48
    ে
    2.46
    也
    2.44
    cg
    2.40
     এসে
    2.37
    cw
    2.28
    quele
    2.25
    这篇文章
    2.25
    Activations Density 0.005%

    No Known Activations