© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 195640
    Prev
    Next
    INDEX
    Explanations

    global followed by specific words

    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_4_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
    не
    1.20
    。
    1.13
    ли
    1.09
    ла
    1.05
    ا۔
    0.95
    시
    0.95
    ле
    0.92
    ან
    0.91
    по
    0.90
    ྥ
    0.90
    POSITIVE LOGITS
    3
    1.30
     as
    1.20
    0
    1.20
    9
    1.18
    2
    1.15
    }
    1.14
    :
    1.14
    ]
    1.13
    4
    1.11
    8
    1.09
    Activations Density 0.000%

    No Known Activations