© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 10155
    Prev
    Next
    INDEX
    Explanations

    mentions of parks, species, or related locations

    oai_token-act-pair · gemini-2.0-flash

    park

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     park
    -2.48
     Park
    -2.38
    Park
    -2.28
     PARK
    -2.19
    park
    -2.02
    PARK
    -1.81
     parks
    -1.73
     Parks
    -1.66
    parks
    -1.41
    Parks
    -1.33
    POSITIVE LOGITS
     nakalista
    0.73
    TemporalType
    0.68
    djangoproject
    0.55
     woj
    0.54
    Rigidbody
    0.53
    owieck
    0.53
     Chry
    0.52
    htbp
    0.52
    (||
    0.52
    ManyToOne
    0.51
    Activations Density 3.374%

    No Known Activations