© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 216037
    Prev
    Next
    INDEX
    Explanations

    school, daycare, teacher, exposure

    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_31_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
    ivr
    0.41
    毫
    0.40
    bell
    0.39
    ताव
    0.38
    存储
    0.37
    descricao
    0.37
    ሆን
    0.37
    ahmatullahi
    0.36
     इंजी
    0.36
    赜
    0.36
    POSITIVE LOGITS
     Delay
    0.41
     iterated
    0.41
     Aran
    0.37
    ត្រូ
    0.37
    ávan
    0.37
    γέν
    0.37
    Iterator
    0.37
     delayed
    0.36
     Goni
    0.36
     disen
    0.36
    Activations Density 0.002%

    No Known Activations