© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 119842
    Prev
    Next
    INDEX
    Explanations

    break down

    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
     locks
    0.41
     rename
    0.40
     XOR
    0.38
    写
    0.38
     replace
    0.37
    nare
    0.37
    POSIX
    0.37
     REPLACE
    0.36
     vacate
    0.36
     obscure
    0.35
    POSITIVE LOGITS
    aupun
    0.42
    越来越多
    0.38
    汛
    0.38
    ിലും
    0.38
     darüber
    0.36
    ளிலும்
    0.36
    ેલા
    0.36
    httpClient
    0.36
    MINUTE
    0.36
    $/../../
    0.35
    Activations Density 0.040%

    No Known Activations