© 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. 5820
    Prev
    Next
    INDEX
    Explanations

    Outer Rim

    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
    𝑒
    2.55
    یه
    2.37
    何
    2.32
    븅
    2.31
    Cpu
    2.31
     Angew
    2.25
    winds
    2.22
    僱
    2.19
    рија
    2.14
    ি
    2.12
    POSITIVE LOGITS
    et
    2.82
    ような
    2.73
    ים
    2.45
    𝐦
    2.43
    ї
    2.40
    𝐧
    2.37
    ﻭ
    2.35
    çe
    2.35
     majoring
    2.32
    pane
    2.29
    Activations Density 0.000%

    No Known Activations