© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 667
    Prev
    Next
    INDEX
    Explanations

    source code and configuration files

    oai_token-act-pair · gemini-2.0-flash

    code/files

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     BoxDecoration
    -0.88
     unknownFields
    -0.85
    sidemargin
    -0.77
    AndEndTag
    -0.76
    XmlAccessorType
    -0.76
     BorderRadius
    -0.75
    AxisAlignment
    -0.73
    SourceChecksum
    -0.72
     дописавши
    -0.72
    ResumeLayout
    -0.71
    POSITIVE LOGITS
     text
    0.68
    Text
    0.61
     Text
    0.59
    text
    0.59
     Waray
    0.56
     textual
    0.51
     TEXT
    0.44
    TEXT
    0.42
    Matic
    0.40
    <!--
    0.40
    Activations Density 5.887%

    No Known Activations