© 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. 5972
    Prev
    Next
    INDEX
    Explanations

    plugin configuration or definitions

    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
    า
    2.22
    𝗸
    2.12
    an
    2.12
    ки
    2.09
     собой
    2.08
    ‍♂️
    2.06
    orylation
    2.05
     \)
    2.02
    ]),
    2.02
    님
    2.01
    POSITIVE LOGITS
     consta
    2.72
    я
    2.51
    ław
    2.29
     ktorý
    2.25
    d
    2.23
     korišten
    2.22
    dě
    2.22
    jó
    2.21
    herokuapp
    2.21
     Collapse
    2.17
    Activations Density 0.000%

    No Known Activations