© 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. 3063
    Prev
    Next
    INDEX
    Explanations

    Yo, check the micYo, let me dropYo, check the pulse

    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
    ation
    2.18
    ך
    1.96
    ة
    1.84
    انی
    1.78
    encies
    1.68
    люби
    1.65
     sane
    1.64
    ياء
    1.62
    ening
    1.60
    말로
    1.60
    POSITIVE LOGITS
    এর
    2.39
    и
    2.25
    or
    2.13
    as
    2.07
    u
    2.07
    '}$
    1.91
    '.$
    1.90
     confounding
    1.80
    ্ড
    1.80
    ir
    1.79
    Activations Density 0.001%

    No Known Activations