© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 77169
    Prev
    Next
    INDEX
    Explanations

    escape from

    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_31_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
    㯎
    0.36
    ilities
    0.35
     मोनो
    0.35
    áne
    0.35
    悹
    0.34
    iph
    0.34
    තා
    0.33
    ipin
    0.33
    éndose
    0.33
    udir
    0.33
    POSITIVE LOGITS
     consecut
    0.34
     convict
    0.33
     ضعف
    0.32
     convicts
    0.32
    ถูก
    0.32
     countable
    0.32
    
    0.32
     consecutively
    0.31
    
    0.31
     imput
    0.30
    Activations Density 0.003%

    No Known Activations