© 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
    2. Gemma-3-27B-IT
    3. 44-GEMMASCOPE-2-TRANSCODER-262K
    4. 105225
    Prev
    Next
    INDEX
    Explanations

    under

    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_44_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
     removed
    0.40
     calcul
    0.37
     Calcula
    0.37
     calculado
    0.36
    哺
    0.36
    🤙
    0.36
     있다는
    0.36
     reloc
    0.35
    ]?
    0.35
     Crac
    0.35
    POSITIVE LOGITS
     Оте
    0.39
    LTE
    0.37
    bbb
    0.37
    bard
    0.37
    Rh
    0.36
    }}^{*
    0.36
    ution
    0.36
     besie
    0.35
    rif
    0.35
    बह
    0.34
    Activations Density 0.002%

    No Known Activations