© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 168186
    Prev
    Next
    INDEX
    Explanations

    providers

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     doing
    0.77
    Doing
    0.75
     Doing
    0.71
     lakukan
    0.64
    doing
    0.59
    做的
    0.55
    做了
    0.54
     做
    0.54
    做到
    0.54
     melakukan
    0.53
    POSITIVE LOGITS
    }}=(
    0.39
     सस्ती
    0.36
    isière
    0.36
     WERE
    0.35
     Plea
    0.35
     }^{(
    0.34
     eye
    0.34
    sequence
    0.34
    。（
    0.33
     Compatible
    0.33
    Activations Density 0.001%

    No Known Activations