© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 120161
    Prev
    Next
    INDEX
    Explanations

    one thing is clear

    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_27_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
    secure
    0.35
    offsetWidth
    0.35
     purse
    0.35
    ỳ
    0.34
     पार्ट
    0.34
    満足
    0.34
     модуля
    0.34
     देन
    0.34
    exchange
    0.33
    ൨
    0.33
    POSITIVE LOGITS
     affirmations
    0.38
     animations
    0.36
    失望
    0.36
     numerosos
    0.35
     numerosas
    0.35
    சார
    0.35
     estarán
    0.34
    teo
    0.33
    लब
    0.33
     certainement
    0.33
    Activations Density 0.001%

    No Known Activations