© 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. 6459
    Prev
    Next
    INDEX
    Explanations

    jasmine

    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
    یوں
    2.44
    ی
    2.40
     яв
    2.39
    όμε
    2.23
    ів
    2.19
     birdseye
    2.18
    𝗶
    2.16
    ল্যান্ড
    2.15
     zato
    2.14
     Wider
    2.10
    POSITIVE LOGITS
    ר
    3.09
    م
    2.96
     mesons
    2.52
     bothered
    2.48
    ナ
    2.43
     martens
    2.39
    ra
    2.36
     pissed
    2.36
     아닌
    2.35
    𝐒
    2.35
    Activations Density 0.011%

    No Known Activations