© 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. 5081
    Prev
    Next
    INDEX
    Explanations

    wispy clouds

    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
    r
    3.57
    er
    3.48
    ្យ
    3.17
    l
    3.05
    ный
    2.98
    اب
    2.92
    ू
    2.88
    ر
    2.83
    hjust
    2.82
    ので
    2.73
    POSITIVE LOGITS
     been
    4.94
    been
    3.80
     sido
    3.45
     BEEN
    3.39
    Been
    3.11
     varit
    3.09
     fui
    3.02
     Been
    2.96
     vært
    2.70
    ahah
    2.70
    Activations Density 0.000%

    No Known Activations