© 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. 6128
    Prev
    Next
    INDEX
    Explanations

    diverse scripts and punctuation

    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
    с
    1.44
    sen
    1.35
    ll
    1.24
     UITableView
    1.18
    сный
    1.17
    sides
    1.17
    نگ
    1.16
    splitContainer
    1.16
    сное
    1.13
    nue
    1.12
    POSITIVE LOGITS
    en
    1.48
    )?,
    1.23
     はい
    1.23
    ার্চ
    1.23
    া
    1.22
    пъл
    1.20
     bulat
    1.20
    然後
    1.20
    )」
    1.19
    ી
    1.19
    Activations Density 0.002%

    No Known Activations