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

    Neuronpedia

    Jacobian LensNEW
    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. 6432
    Prev
    Next
    INDEX
    Explanations

    how to explain processes

    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
    keepers
    1.15
    কি
    1.11
     reputable
    1.09
    ない
    1.06
    т
    1.06
     불구하고
    1.05
    uctive
    1.03
    こちらの
    1.03
     जमकर
    1.01
    вод
    1.01
    POSITIVE LOGITS
    𝓪
    1.45
    𝖓
    1.44
    ects
    1.36
    opcode
    1.34
    𝘢
    1.34
     nags
    1.30
    ى
    1.27
     peau
    1.27
     bilge
    1.26
    ના
    1.26
    Activations Density 0.233%

    No Known Activations