© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 5727
    Prev
    Next
    INDEX
    Explanations

    async () => { }

    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
    er
    2.38
    it
    2.22
    و
    2.18
    ва
    2.09
    いえ
    2.07
    paul
    2.03
     éditions
    2.01
    mmas
    2.01
    lon
    2.00
    게
    2.00
    POSITIVE LOGITS
    龴
    2.81
    за
    2.79
    viewModel
    2.56
    𝘤
    2.51
    О
    2.42
    $("
    2.39
    𝘳
    2.38
    зать
    2.37
    𝘴
    2.25
    𝘰
    2.22
    Activations Density 0.002%

    No Known Activations