© 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. 5249
    Prev
    Next
    INDEX
    Explanations

    code assignment/declaration

    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
    होस्
    2.31
    蟲
    2.20
     alle
    2.17
     neutralizing
    2.15
    ки
    2.15
    )])
    2.12
    нения
    2.09
    mData
    2.04
    xFF
    2.03
    ့
    2.01
    POSITIVE LOGITS
    та
    2.63
    тала
    2.13
    Wage
    2.05
    ˗
    2.00
     bolted
    1.86
    kurs
    1.86
    는
    1.83
    ına
    1.83
    ////////////////
    1.80
    ništ
    1.80
    Activations Density 0.053%

    No Known Activations