© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 18893
    Prev
    Next
    INDEX
    Explanations

    school students

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_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
     Substitute
    0.45
    的操作
    0.43
    लू
    0.42
    Substitute
    0.40
    操作
    0.39
     Graduation
    0.39
     doskona
    0.36
    겐
    0.36
    Worker
    0.36
     жар
    0.36
    POSITIVE LOGITS
     studying
    1.34
     Studying
    1.19
     अध्ययन
    1.07
     studied
    1.03
     estudar
    1.03
     estudiar
    1.03
     estudiando
    1.02
     study
    1.02
    study
    1.01
     estudia
    1.00
    Activations Density 0.040%

    No Known Activations