© 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-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 156676
    Prev
    Next
    INDEX
    Explanations

    mole

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    ITI
    0.47
    itri
    0.45
    об
    0.44
    iti
    0.43
     ł
    0.41
     Fah
    0.41
    ti
    0.41
    亭
    0.41
    ન્ટે
    0.40
    onta
    0.40
    POSITIVE LOGITS
     moles
    0.46
     mole
    0.41
     CMC
    0.41
    ichés
    0.39
     Mole
    0.39
     TOW
    0.39
    DIC
    0.38
    dic
    0.38
    ధ్య
    0.36
    чик
    0.36
    Activations Density 0.003%

    No Known Activations