© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 204501
    Prev
    Next
    INDEX
    Explanations

    Zelda games

    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
    碩
    0.39
     posti
    0.37
    Tocco
    0.37
    ἠ
    0.36
    হন
    0.36
     productor
    0.35
     produ
    0.35
    asper
    0.35
    }^{+},
    0.35
    ަމ
    0.35
    POSITIVE LOGITS
    zv
    0.44
     Keenan
    0.42
     Kor
    0.41
     kor
    0.40
     Robin
    0.40
     корпуса
    0.40
    oplasma
    0.39
    कोर
    0.39
    coroutines
    0.39
     Zem
    0.38
    Activations Density 0.002%

    No Known Activations