© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 44283
    Prev
    Next
    INDEX
    Explanations

    bonobo baboon

    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_3_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
    \
    0.82
    ส
    0.72
    ır
    0.71
    जा
    0.70
    อน
    0.68
    รถ
    0.66
    ]
    0.66
    งาน
    0.65
    ],
    0.64
     ی
    0.63
    POSITIVE LOGITS
    l
    1.01
    n
    0.90
    x
    0.89
    r
    0.84
    d
    0.79
    at
    0.74
    t
    0.74
    lina
    0.72
    lcl
    0.71
    lés
    0.71
    Activations Density 0.002%

    No Known Activations