© 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. 6073
    Prev
    Next
    INDEX
    Explanations

    code examples and instructions

    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
    س
    2.20
    ح
    2.04
    it
    1.96
    м
    1.82
    et
    1.79
    ek
    1.76
    ic
    1.70
    ec
    1.68
    ை
    1.67
    ﻢ
    1.66
    POSITIVE LOGITS
    ﻱ
    1.66
    land
    1.62
    রিটি
    1.59
    yyyyyyyy
    1.56
     mattina
    1.56
     apre
    1.52
    ر
    1.50
    ians
    1.49
    CRT
    1.49
    ﻗ
    1.46
    Activations Density 0.004%

    No Known Activations