© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 299
    Prev
    Next
    INDEX
    Explanations

    hyphenated alphanumeric strings and discriminatory language, and numbers like 34 and 12

    oai_token-act-pair · gemini-2.0-flash

    hyphen

    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
     Roskov
    -0.57
    GEBURTSDATUM
    -0.55
    cloudfront
    -0.52
    providedIn
    -0.47
    fare
    -0.46
    хьтан
    -0.46
    UserScript
    -0.45
    ynchronously
    -0.43
    XmlAccessType
    -0.42
    fully
    -0.41
    POSITIVE LOGITS
    by
    1.02
    bies
    0.83
    bes
    0.79
    BY
    0.76
    be
    0.75
    bless
    0.74
    bam
    0.73
    bie
    0.73
    bys
    0.72
    bien
    0.71
    Activations Density 3.712%

    No Known Activations