© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 151042
    Prev
    Next
    INDEX
    Explanations

    addresses Cox recommendations

    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_18_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
    交互
    0.50
     मेघा
    0.47
    鋲
    0.46
     inser
    0.46
     REACTOR
    0.45
     giriyoruz
    0.45
     évo
    0.45
    DS
    0.44
    UIL
    0.44
    缫
    0.43
    POSITIVE LOGITS
    телем
    0.46
    anel
    0.44
     करे
    0.42
     misplaced
    0.41
     recommendations
    0.41
     owning
    0.41
     preferences
    0.41
     attract
    0.40
    тным
    0.40
     anyway
    0.40
    Activations Density 0.000%

    No Known Activations