© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6155
    Prev
    Next
    INDEX
    Explanations

    phrases that appear to signal an exception or caveat in the text

    oai_token-act-pair · gemini-2.0-flash

    technical terms or identifiers in code or documentation

    np_token-act-pair-logits · gpt-4o-mini

    technical contexts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    اعمال
    -0.54
    blers
    -0.53
     تانيه
    -0.52
    ilarang
    -0.52
     дописавши
    -0.51
    ěst
    -0.51
    mListener
    -0.50
     produisons
    -0.50
    Frat
    -0.50
    حوالہ
    -0.49
    POSITIVE LOGITS
    ValueStyle
    0.69
    VersionUID
    0.59
     protoimpl
    0.52
    posedge
    0.49
    enumi
    0.49
    ↘
    0.47
    omyces
    0.46
    DotNetBar
    0.45
    pacho
    0.44
    setStart
    0.44
    Activations Density 9.821%

    No Known Activations