© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 202192
    Prev
    Next
    INDEX
    Explanations

    through + noun phrase

    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
     from
    1.14
     d
    1.05
     dari
    1.02
     di
    1.02
     b
    0.99
     l
    0.98
     dei
    0.98
     by
    0.95
     N
    0.93
     dua
    0.91
    POSITIVE LOGITS
    し
    0.95
    JScripts
    0.92
    Calif
    0.89
    лып
    0.84
    ذف
    0.84
    ሉት
    0.84
    ፈላጊ
    0.83
    Coref
    0.82
    ም።
    0.80
    helps
    0.80
    Activations Density 0.003%

    No Known Activations