© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 215581
    Prev
    Next
    INDEX
    Explanations

    short memory

    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_16_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
    溸
    0.49
     -&
    0.47
    滑动
    0.47
    流动
    0.44
    图中
    0.44
    policy
    0.43
     专业
    0.42
    阶
    0.42
    များသည်
    0.42
    观
    0.42
    POSITIVE LOGITS
     fac
    0.48
     definitely
    0.47
     приня
    0.46
    as
    0.45
     buenos
    0.45
    ized
    0.45
    ing
    0.44
     hac
    0.44
    after
    0.44
     gav
    0.43
    Activations Density 0.000%

    No Known Activations