© 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. 8929
    Prev
    Next
    INDEX
    Explanations

    common short words like prepositions and articles

    oai_token-act-pair · gemini-2.0-flash

    Location

    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
    inalis
    -0.40
    krivning
    -0.40
    kháu
    -0.39
    conomie
    -0.39
    ngulo
    -0.38
    /$',
    -0.38
    blaze
    -0.38
    udesta
    -0.37
    SerializedName
    -0.37
    ActivityCompat
    -0.36
    POSITIVE LOGITS
     outside
    2.00
     inside
    1.98
    outside
    1.78
    inside
    1.65
     underneath
    1.58
     beneath
    1.58
     behind
    1.53
     OUTSIDE
    1.53
    Outside
    1.52
     below
    1.47
    Activations Density 9.769%

    No Known Activations