© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 253355
    Prev
    Next
    INDEX
    Explanations

    say earn

    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_56_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
     sedent
    0.43
     exposureButton
    0.40
    োই
    0.39
     Inge
    0.35
     ہوگئی
    0.35
    ကျော်
    0.34
     rag
    0.34
    ໋
    0.34
     ваши
    0.34
    ЭС
    0.34
    POSITIVE LOGITS
    ear
    2.30
     ear
    2.30
    Ear
    2.17
     Ear
    2.16
     EAR
    1.98
    EAR
    1.88
     earn
    1.84
    耳
    1.84
     earl
    1.81
    Earl
    1.73
    Activations Density 0.002%

    No Known Activations