© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 8386
    Prev
    Next
    INDEX
    Explanations

    apologies; I'm sorry

    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
    𝐡
    1.17
    𝐝
    1.08
    mdash
    1.08
    ége
    1.06
    𝐢
    1.01
     Он
    1.01
    ра
    1.00
    𝐫
    1.00
    ४
    0.98
     Él
    0.96
    POSITIVE LOGITS
    ு
    1.23
    고
    1.22
    л
    1.22
    ться
    1.17
    こちらの
    1.15
    खु
    1.11
    رى
    1.09
    न
    1.08
    ر
    1.07
     সেগুলো
    1.06
    Activations Density 0.261%

    No Known Activations