© 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. 132458
    Prev
    Next
    INDEX
    Explanations

    site

    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
    )
    1.45
    ;
    1.18
    мого
    0.78
     high
    0.75
    ).
    0.74
    '
    0.74
     ')
    0.73
    hen
    0.73
    ]
    0.73
     u
    0.71
    POSITIVE LOGITS
    كان
    1.25
    h
    1.20
    يل
    1.19
     حسين
    1.17
    كس
    1.14
    ة
    1.08
     سعيد
    1.05
    С
    1.04
     دي
    1.02
    లో
    1.02
    Activations Density 0.000%

    No Known Activations