© 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. 53171
    Prev
    Next
    INDEX
    Explanations

    poetic language and voice

    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
    ത്യാ
    0.26
    θε
    0.26
     বন্ধুত্ব
    0.25
    শক
    0.25
     பிச்சு
    0.25
    ㄌ
    0.25
    튿
    0.25
     numeral
    0.25
     прис
    0.25
    \"]\
    0.24
    POSITIVE LOGITS
     beetle
    0.25
    Apparently
    0.22
    ()).
    0.22
     Stand
    0.22
    یں۔
    0.22
    Cardiac
    0.22
    ľa
    0.22
     undergone
    0.21
    GC
    0.21
     WSA
    0.21
    Activations Density 0.009%

    No Known Activations