© 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. 3724
    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
    ون
    2.50
     seja
    2.46
    א
    2.43
    ₽
    2.38
    ፍተኛ
    2.35
    ০০
    2.34
    ़
    2.34
    verläss
    2.33
     vignettes
    2.32
    9
    2.31
    POSITIVE LOGITS
    t
    4.19
    tive
    3.29
    natal
    3.14
    nt
    3.11
    lle
    3.02
    timed
    3.00
    ش
    2.98
    ことがあります
    2.95
    rind
    2.91
    tib
    2.89
    Activations Density 0.118%

    No Known Activations