© 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. 4106
    Prev
    Next
    INDEX
    Explanations

    single uppercase letters or short sequences of uppercase letters, especially those related to biology, code, or chemistry

    oai_token-act-pair · gemini-2.0-flash

    Molecular biology

    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
    I
    -1.34
    A
    -0.82
    B
    -0.69
    riwal
    -0.65
    Ii
    -0.60
    E
    -0.58
    O
    -0.54
    IEM
    -0.54
    Ij
    -0.54
    Ea
    -0.54
    POSITIVE LOGITS
    الحياه
    0.56
    SharedDtor
    0.53
    UnknownFieldSet
    0.51
    rawdę
    0.49
    XmlAccessType
    0.47
    Примі
    0.46
    ről
    0.46
    Referanser
    0.45
    findpost
    0.44
    mographie
    0.44
    Activations Density 3.564%

    No Known Activations