© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 4836
    Prev
    Next
    INDEX
    Explanations

    sweet spot

    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
    l
    4.20
    an
    3.81
    r
    3.39
    b
    3.20
    quela
    3.17
     abbreviation
    3.10
    ন
    3.07
    л
    3.05
     estime
    3.03
    ల
    3.02
    POSITIVE LOGITS
    ی
    4.19
     priori
    2.89
     partir
    2.82
    는
    2.81
     fate
    2.80
    լ
    2.70
    pytest
    2.69
    lijke
    2.69
    θα
    2.68
     pointer
    2.64
    Activations Density 0.000%

    No Known Activations