© 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. 6177
    Prev
    Next
    INDEX
    Explanations

    text referencing Jewish and Christian religious and political views, particularly related to Zionism and Israel

    oai_token-act-pair · gemini-2.0-flash

    race, conflict, and history

    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
    AndEndTag
    -0.53
    lectricité
    -0.53
     ExecuteAsync
    -0.50
    AutoresizingMask
    -0.48
     decoradas
    -0.47
     linkovi
    -0.47
    enterOuterAlt
    -0.46
    artige
    -0.46
    imarães
    -0.45
     AppCompatTheme
    -0.45
    POSITIVE LOGITS
    GOTREF
    0.65
    EditorBrowsable
    0.63
     CreateTagHelper
    0.57
    ResponseWriter
    0.57
     sadd
    0.57
    ioutil
    0.57
     ottoman
    0.56
    Xaml
    0.56
    MLLoader
    0.56
     chur
    0.55
    Activations Density 13.009%

    No Known Activations