© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    4. 3394
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_5_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
     timely
    1.33
    لک
    1.32
    ӡ
    1.26
    ൺലൈ
    1.26
     AsRef
    1.26
     radiation
    1.23
     rangement
    1.23
    ट्रोल
    1.23
     уж
    1.22
     ggtitle
    1.22
    POSITIVE LOGITS
    od
    1.30
    İ
    1.18
    en
    1.15
     immer
    1.13
     ilang
    1.11
    tod
    1.10
    about
    1.09
     esti
    1.09
    }+
    1.08
    atform
    1.07
    Activations Density 0.000%

    No Known Activations