© 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
    2. Gemma-3-4B-IT
    3. 25-GEMMASCOPE-2-TRANSCODER-262K
    4. 9173
    Prev
    Next
    INDEX
    Explanations

    1

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_25_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
    ﹞
    0.89
     Découvrez
    0.81
    ússia
    0.75
    ),
    0.74
    )\,
    0.74
    〕
    0.71
     зустрі
    0.70
    --)
    0.70
    ),'
    0.70
    _),
    0.69
    POSITIVE LOGITS
     Open
    0.92
     opened
    0.90
     open
    0.89
    Open
    0.87
    Opening
    0.86
     opens
    0.86
     opening
    0.84
    open
    0.83
     Opens
    0.83
     Opening
    0.80
    Activations Density 0.025%

    No Known Activations