© 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. 11958
    Prev
    Next
    INDEX
    Explanations

    proper nouns, countries, and companies, often in a financial or geopolitical context

    oai_token-act-pair · gemini-2.0-flash

    Nationalities

    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
    )))));
    -0.51
    scream
    -0.47
    Condol
    -0.47
    osoever
    -0.45
     U
    -0.45
     of
    -0.44
     gratefully
    -0.43
    lıkla
    -0.43
    Invalidate
    -0.43
     beseech
    -0.42
    POSITIVE LOGITS
    AndEndTag
    0.81
     kasarigan
    0.79
     Administrativna
    0.75
    RTEX
    0.73
    rungsseite
    0.73
    OGND
    0.71
     يتيمه
    0.69
    Obrázky
    0.69
     pulumi
    0.68
    UserScript
    0.68
    Activations Density 8.174%

    No Known Activations