© 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. 6205
    Prev
    Next
    INDEX
    Explanations

    legal and medical language around prevention and drastic remedies

    oai_token-act-pair · gemini-2.0-flash

    technical terms and legal jargon

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

    legal/criminal actions

    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
     AssemblyVersion
    -0.57
    forChild
    -0.55
    .*")]
    -0.51
    ⓧ
    -0.50
    ftn
    -0.50
     réessayer
    -0.50
    jgl
    -0.49
    <{
    -0.49
     MonoBehaviour
    -0.48
     препратки
    -0.47
    POSITIVE LOGITS
     Suivez
    0.52
    CAPTION
    0.52
    ]")]
    0.51
     Deutschlands
    0.49
    Rcpp
    0.48
     nargin
    0.48
    Datuak
    0.48
    presso
    0.48
     décou
    0.47
     Letters
    0.47
    Activations Density 4.151%

    No Known Activations