© 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
    2. Gemma-3-4B-IT
    3. 5-GEMMASCOPE-2-TRANSCODER-262K
    4. 3055
    Prev
    Next
    INDEX
    Explanations

    room and board or nights

    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
     prue
    1.72
    さて
    1.55
    ّه
    1.52
    𝐒
    1.50
     जमाने
    1.48
     ediciones
    1.43
     obsolete
    1.43
     Pueblo
    1.42
     ascetic
    1.39
    ve
    1.39
    POSITIVE LOGITS
    ли
    1.72
    가
    1.64
    রা
    1.64
     cris
    1.53
    Berat
    1.51
     reluctant
    1.42
    quire
    1.41
     pozorn
    1.41
    กระจ
    1.41
    &$\
    1.40
    Activations Density 0.001%

    No Known Activations