© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 7141
    Prev
    Next
    INDEX
    Explanations

    holding back

    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
     ilg
    2.91
     Trouvez
    2.57
     stuffed
    2.37
    utter
    2.29
    𝗈
    2.23
    yce
    2.23
    jeu
    2.23
    naya
    2.22
     oli
    2.21
    Shortly
    2.17
    POSITIVE LOGITS
     lawfully
    2.57
    ്രി
    2.53
    ι
    2.41
    ња
    2.36
     thước
    2.34
    ∈
    2.33
    ї
    2.28
     thumbnail
    2.26
    интере
    2.24
    conoc
    2.21
    Activations Density 0.004%

    No Known Activations