© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 528
    Prev
    Next
    INDEX
    Explanations

    hearsay within hearsay

    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
     prosecuted
    0.47
     acquittal
    0.46
     sentencing
    0.46
     convict
    0.45
     Prosecution
    0.43
     prosec
    0.43
     convicted
    0.43
    銮
    0.43
     prosecution
    0.42
     perp
    0.41
    POSITIVE LOGITS
     হাব
    0.48
    维
    0.40
     EVP
    0.39
     ഭൂ
    0.38
     האט
    0.38
     जावेद
    0.38
     Ex
    0.38
    Javadoc
    0.38
     إجراء
    0.37
    électricité
    0.37
    Activations Density 0.011%

    No Known Activations