© 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. 17633
    Prev
    Next
    INDEX
    Explanations

    directly related to frontline

    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
     fl
    0.37
     socio
    0.36
    瓢
    0.36
     bluegrass
    0.36
     fragmentation
    0.36
     अनिल
    0.36
     Medieval
    0.34
     تكعيب
    0.34
     velvet
    0.34
    .+
    0.34
    POSITIVE LOGITS
     frontline
    0.68
    可以直接
    0.46
     непосредственно
    0.45
     مباشرة
    0.45
    Front
    0.44
     фрон
    0.44
    classroom
    0.44
    臨床
    0.44
     direttamente
    0.43
     doğrudan
    0.42
    Activations Density 0.052%

    No Known Activations