© 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. 6928
    Prev
    Next
    INDEX
    Explanations

    code snippets or technical documentation related to web development

    oai_token-act-pair · gemini-2.0-flash

    Web development context

    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
    RegressionTest
    -0.66
     utafitiHapana
    -0.65
    apunov
    -0.64
    QMetaType
    -0.59
    smithy
    -0.57
    parsedMessage
    -0.57
    elemField
    -0.56
     Normdatei
    -0.56
     pleaſure
    -0.54
    qtype
    -0.54
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.66
     onCancelled
    0.59
    AndEndTag
    0.58
    SequentialGroup
    0.47
    )))),
    0.47
     jy
    0.47
    Ifc
    0.46
     plotly
    0.45
    archiviato
    0.45
    ISPR
    0.45
    Activations Density 25.021%

    No Known Activations