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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12054
    Prev
    Next
    INDEX
    Explanations

    program code syntax.

    oai_token-act-pair · gemini-2.0-flash

    ]

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <bos>
    -1.76
    ]
    -1.68
    .]
    -1.19
     ]
    -1.18
    ].
    -1.14
    ])
    -1.06
    ],
    -1.00
    "]
    -0.93
    ]$
    -0.93
    ]:
    -0.92
    POSITIVE LOGITS
    +#+#
    1.04
    fjspx
    0.96
    MemoryWarning
    0.94
    GraphicsUnit
    0.93
    AutoScaleMode
    0.85
     resourceCulture
    0.84
    WebElementEntity
    0.80
    igshid
    0.78
     BoxFit
    0.77
    matchCondition
    0.76
    Activations Density 3.900%

    No Known Activations