© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 209764
    Prev
    Next
    INDEX
    Explanations

    species following vibrio

    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_20_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
    ্লাম
    0.41
     injective
    0.39
    編
    0.38
     dilute
    0.38
    掺
    0.38
    াস
    0.37
     knowingly
    0.37
    劣
    0.37
    GetObject
    0.37
     posterity
    0.37
    POSITIVE LOGITS
    inka
    0.53
     murder
    0.49
    irà
    0.49
     kafka
    0.48
    hese
    0.47
     morts
    0.47
     čp
    0.47
     disparu
    0.45
     Mena
    0.45
    ka
    0.45
    Activations Density 0.000%

    No Known Activations