© 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. 7164
    Prev
    Next
    INDEX
    Explanations

    help me

    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
    ン
    2.89
    ే
    2.22
    ν
    2.20
     userRoutes
    2.14
    ル
    2.12
     sentimos
    2.10
     phonons
    2.08
    р
    2.07
    й
    2.04
    ை
    2.03
    POSITIVE LOGITS
    𝐝
    2.12
    𝐦
    2.06
    mt
    1.89
    ablement
    1.79
    gub
    1.77
    𝐭
    1.76
    клад
    1.75
    atham
    1.75
     जाकर
    1.75
    메이션
    1.73
    Activations Density 0.141%

    No Known Activations