© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 203946
    Prev
    Next
    INDEX
    Explanations

    exploration and rus

    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_6_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
    da
    0.71
    ac
    0.70
    ge
    0.70
    c
    0.70
    s
    0.64
    k
    0.64
    st
    0.63
    ation
    0.62
    g
    0.61
    ib
    0.60
    POSITIVE LOGITS
     hypothes
    0.49
     décrire
    0.45
     constitu
    0.45
     constru
    0.44
    ﻒ
    0.44
     nuclé
    0.44
     examin
    0.44
     tòa
    0.44
     squre
    0.43
     réaliser
    0.43
    Activations Density 0.000%

    No Known Activations