© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 77988
    Prev
    Next
    INDEX
    Explanations

    company name changes

    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_31_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
     esquerda
    0.36
    ilar
    0.36
    gangenheit
    0.35
    安
    0.35
    埋
    0.35
    ogan
    0.35
    Explain
    0.34
    డ
    0.34
     সাধন
    0.34
     stumps
    0.34
    POSITIVE LOGITS
     renaming
    0.50
     rename
    0.48
     renamed
    0.46
     rebranding
    0.46
     تغییر
    0.45
     Rename
    0.43
     blending
    0.43
     merging
    0.43
     зміню
    0.42
    合并
    0.42
    Activations Density 0.005%

    No Known Activations