© 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
    2. Gemma-3-4B-IT
    3. 3-GEMMASCOPE-2-TRANSCODER-262K
    4. 5792
    Prev
    Next
    INDEX
    Explanations

    specificity

    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
    años
    3.02
    el
    2.69
     fatta
    2.68
    yyyyyyyy
    2.48
     dernières
    2.47
    蕩
    2.46
    é
    2.37
    荡
    2.35
    amme
    2.35
    esian
    2.31
    POSITIVE LOGITS
    یات
    2.55
     detriment
    2.40
    ма
    2.34
     rumin
    2.25
    মতো
    2.22
     eloquently
    2.16
     bac
    2.15
     volition
    2.08
    textField
    2.07
     waktu
    2.07
    Activations Density 0.185%

    No Known Activations