© 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. 4771
    Prev
    Next
    INDEX
    Explanations

    justify

    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
     hydrodynamic
    3.10
    я
    2.98
    ිට
    2.84
     confocal
    2.81
    holen
    2.79
    kjav
    2.79
    ر
    2.76
    tive
    2.75
    hate
    2.73
     isotopic
    2.66
    POSITIVE LOGITS
    ifiably
    3.52
     aces
    2.69
    cbd
    2.66
    সঙ্গত
    2.63
     jazdy
    2.62
    ⟶
    2.59
     pesca
    2.56
     moieties
    2.51
     положения
    2.51
    ያንዳ
    2.49
    Activations Density 0.040%

    No Known Activations