© 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. 203897
    Prev
    Next
    INDEX
    Explanations

    as per the

    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
    .
    1.27
    ion
    0.96
    ٹری
    0.89
    ure
    0.88
    iche
    0.86
    odo
    0.85
    uran
    0.85
    ether
    0.84
    ulus
    0.79
    ورد
    0.79
    POSITIVE LOGITS
    p
    1.52
    на
    1.33
    ;
    1.30
    ন
    1.16
    자
    1.15
    },
    1.12
     to
    1.09
    siniz
    1.08
     insolvent
    1.07
    m
    1.06
    Activations Density 0.000%

    No Known Activations