© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 143097
    Prev
    Next
    INDEX
    Explanations

    early

    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_46_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
     bewegen
    0.43
    CTION
    0.40
    YNAMICS
    0.39
    淐
    0.39
    ﻈ
    0.38
    uncture
    0.38
    حر
    0.38
     ION
    0.38
     взрос
    0.36
    ät
    0.36
    POSITIVE LOGITS
    life
    0.46
     life
    0.45
     vida
    0.43
    जीवन
    0.42
     Life
    0.39
     життя
    0.39
    ]],
    0.39
    জীবন
    0.38
     extinction
    0.38
    ))).
    0.38
    Activations Density 0.002%

    No Known Activations