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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 14741
    Prev
    Next
    INDEX
    Explanations

    math and symbolic notation.

    oai_token-act-pair · gemini-2.0-flash

    code and formulas

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     photolibrary
    -0.68
     becauſe
    -0.67
     auffi
    -0.59
     bogotá
    -0.58
     itſelf
    -0.58
     Shakspeare
    -0.57
    ̈́
    -0.57
     moschino
    -0.57
     pngtree
    -0.56
     myſelf
    -0.56
    POSITIVE LOGITS
    enumi
    0.81
    PYX
    0.68
    multicolumn
    0.67
    EREF
    0.67
     se
    0.66
     }
    0.65
    +}$
    0.65
    "](
    0.65
    MockBean
    0.64
    ]-->
    0.63
    Activations Density 32.925%

    No Known Activations