© 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. 232556
    Prev
    Next
    INDEX
    Explanations

    alignment

    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
     spying
    0.41
    )]),
    0.38
     ছুটি
    0.37
    𝗺
    0.37
    caches
    0.36
    reira
    0.36
     rocky
    0.35
    クレ
    0.35
     பளி
    0.34
     grub
    0.34
    POSITIVE LOGITS
    Centered
    0.58
     centered
    0.55
    centered
    0.55
     centred
    0.52
     පිළ
    0.48
    ^{+}$
    0.45
    centred
    0.45
     alphabetically
    0.44
     merkez
    0.42
     furnish
    0.41
    Activations Density 0.000%

    No Known Activations