© 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. 24-GEMMASCOPE-TRANSCODER-16K
    4. 539
    Prev
    Next
    INDEX
    Explanations

    words related to definitions of words or phrases and whether they have multiple meanings

    oai_token-act-pair · gemini-2.0-flash

    meaning and interpretations

    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
     meaning
    -2.59
    Meaning
    -2.41
     Meaning
    -2.36
    meaning
    -2.25
     meanings
    -2.03
     means
    -2.02
     MEAN
    -1.80
     Means
    -1.80
    means
    -1.77
    Means
    -1.75
    POSITIVE LOGITS
    ietf
    0.52
    providedIn
    0.48
    rxjs
    0.46
    verifyException
    0.44
     getSystem
    0.43
    fromnode
    0.41
     ')[
    0.41
     _:
    0.40
    راتيج
    0.40
    物的
    0.40
    Activations Density 2.430%

    No Known Activations