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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 5563
    Prev
    Next
    INDEX
    Explanations

    collections of valuable items

    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
     loving
    2.70
    一个
    2.59
    cpf
    2.51
    ن
    2.33
    ్‌
    2.33
    е
    2.29
    ાર્થી
    2.26
    }^{*}
    2.24
    ні
    2.21
    ArrayAdapter
    2.18
    POSITIVE LOGITS
    ively
    2.89
    Архівовано
    2.62
     cosecha
    2.48
    вичайно
    2.36
    னர்
    2.35
    ya
    2.34
    ന്യൂ
    2.33
    sono
    2.30
     admire
    2.29
     andare
    2.21
    Activations Density 0.053%

    No Known Activations