© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 24150
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
     frequently
    0.50
    ]',
    0.47
     understanding
    0.45
     mogą
    0.44
    understanding
    0.44
    Frequently
    0.42
    罹
    0.42
    ]],
    0.40
    ²',
    0.40
    »،
    0.40
    POSITIVE LOGITS
     min
    0.44
    nish
    0.41
     minh
    0.40
     Min
    0.39
    min
    0.38
     Background
    0.38
    ・・
    0.38
     Comptes
    0.38
     мин
    0.38
     minuten
    0.38
    Activations Density 0.002%

    No Known Activations