© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 152435
    Prev
    Next
    INDEX
    Explanations

    internet and speech restrictions

    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_23_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
    镀
    0.44
    至於
    0.42
     фина
    0.41
     Matthew
    0.40
    Matthew
    0.40
     deterrent
    0.39
     प्रशिक्षण
    0.38
    茦
    0.38
     preferentially
    0.38
    沢山
    0.37
    POSITIVE LOGITS
    悶
    0.41
    esty
    0.39
    endl
    0.38
    )\|
    0.37
     berl
    0.37
     Regression
    0.36
     농
    0.36
    klore
    0.36
     ඔබ
    0.36
     calmness
    0.36
    Activations Density 0.001%

    No Known Activations