© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 16077
    Prev
    Next
    INDEX
    Explanations

    the phrase "at this point"

    oai_token-act-pair · gemini-2.0-flash

    a circumstance

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    featureID
    -0.97
     GenerationType
    -0.94
    AndEndTag
    -0.91
     '\\;'
    -0.90
    richTextPanel
    -0.89
     ProtoMessage
    -0.85
    ConstraintMaker
    -0.85
    LEncoder
    -0.84
     unknownFields
    -0.82
    AccessorTable
    -0.82
    POSITIVE LOGITS
    сли
    0.39
    po
    0.36
    the
    0.36
    ּ
    0.35
    ή
    0.35
    pis
    0.34
    pi
    0.33
     terap
    0.32
     pom
    0.31
     strdup
    0.31
    Activations Density 6.350%

    No Known Activations