© 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. 7628
    Prev
    Next
    INDEX
    Explanations

    neo4j chain

    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
    كيد
    2.30
     expans
    2.24
     developments
    2.15
     اكيد
    2.14
    퐫
    2.13
     incluso
    2.10
    ف
    2.09
     regress
    2.08
     deem
    2.07
     kako
    2.06
    POSITIVE LOGITS
    y
    2.68
    ように
    2.62
    j
    2.50
    ি
    2.47
    ল
    2.46
    le
    2.42
    ようになりました
    2.42
    it
    2.42
    stva
    2.41
    𝑑
    2.36
    Activations Density 0.017%

    No Known Activations