© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 6736
    Prev
    Next
    INDEX
    Explanations

    nameserver services

    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
    و
    3.63
     나서
    2.63
     apoi
    2.35
    jenigen
    2.26
     desses
    2.16
    帙
    2.07
    en
    2.00
    ಾಟ
    1.99
     overwhel
    1.96
    ו
    1.94
    POSITIVE LOGITS
    clarinet
    2.41
    й
    2.40
    𝚘
    2.30
    𝚝
    2.30
    𝚎
    2.25
    𝚛
    2.22
    ন্তন
    2.21
    𝓮
    2.18
    ীয়
    2.14
    ה
    2.13
    Activations Density 0.025%

    No Known Activations