© 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. 738
    Prev
    Next
    INDEX
    Explanations

    pressure drop

    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
     कार्ब
    0.43
    ებმა
    0.42
    留
    0.42
     Кон
    0.39
     VB
    0.39
     Bitmap
    0.39
    ]->
    0.38
    ᖅ
    0.38
    бре
    0.37
    compatibility
    0.37
    POSITIVE LOGITS
     calibrate
    0.38
    agog
    0.37
     :}
    0.37
     AG
    0.36
    딕
    0.36
    chow
    0.36
     خس
    0.35
     sawa
    0.34
    loss
    0.34
     }\
    0.34
    Activations Density 0.007%

    No Known Activations