© 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. 3301
    Prev
    Next
    INDEX
    Explanations

    town or village names

    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
    েল
    0.53
    л
    0.53
     curbing
    0.50
    ياً
    0.49
     equating
    0.49
     tenths
    0.47
     redeemed
    0.46
    сам
    0.46
     highlighting
    0.46
     diff
    0.46
    POSITIVE LOGITS
     zasad
    0.47
    ε
    0.47
    সেল
    0.43
    day
    0.43
    usine
    0.43
     બધા
    0.43
     पीना
    0.43
    おい
    0.42
    +}$
    0.41
    <unused73>
    0.40
    Activations Density 0.009%

    No Known Activations