© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3340
    Prev
    Next
    INDEX
    Explanations

    eyes

    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_5_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
     esistono
    1.47
    бні
    1.39
    ⿷
    1.35
     éventuellement
    1.30
     harmonique
    1.29
    ਪਣ
    1.28
    Ket
    1.28
     suena
    1.28
    তম
    1.28
     привіт
    1.26
    POSITIVE LOGITS
    IsTrue
    1.46
    ن
    1.43
    eyed
    1.42
    썹
    1.42
    ير
    1.41
    आ
    1.40
     apertures
    1.40
     Möglich
    1.36
    此外
    1.30
     eyes
    1.30
    Activations Density 0.095%

    No Known Activations