© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    4. 166829
    Prev
    Next
    INDEX
    Explanations

    introductory phrases

    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_56_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
     então
    0.43
     બહાર
    0.42
    alers
    0.41
    然后
    0.41
     තම
    0.39
     اولا
    0.39
    Hitting
    0.39
    $[\
    0.39
     insieme
    0.39
    一起
    0.38
    POSITIVE LOGITS
    )]
    0.62
    )];
    0.50
    ful
    0.49
     ful
    0.48
    ])
    0.45
    ]
    0.45
    ]-
    0.44
    )])
    0.43
    )].
    0.42
    )]$
    0.41
    Activations Density 0.000%

    No Known Activations