© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 18444
    Prev
    Next
    INDEX
    Explanations

    ocean acidification

    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_34_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
    Boost
    0.39
    扫
    0.38
    mounted
    0.37
    Broad
    0.36
    nous
    0.36
     dropbox
    0.36
    Leaks
    0.35
    Dutch
    0.35
     mickey
    0.35
    Mounted
    0.35
    POSITIVE LOGITS
     ocean
    0.61
     Oregon
    0.58
     Ocean
    0.56
     acidification
    0.56
    酸
    0.55
     Acid
    0.54
     acid
    0.54
    Acid
    0.53
     acidic
    0.52
    Ocean
    0.50
    Activations Density 0.018%

    No Known Activations