© 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. 253449
    Prev
    Next
    INDEX
    Explanations

    met or led

    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
    ,"%
    0.39
    ,"+
    0.39
    )+"]
    0.38
    }"),
    0.37
     regresar
    0.37
    娉
    0.37
    "),],
    0.36
     "):
    0.36
     እንደ
    0.36
    "]);
    0.35
    POSITIVE LOGITS
    Met
    0.52
     Met
    0.51
    met
    0.46
     met
    0.45
    led
    0.42
    ')->
    0.41
    MET
    0.41
    click
    0.40
     following
    0.40
    →
    0.39
    Activations Density 0.000%

    No Known Activations