© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10444
    Prev
    Next
    INDEX
    Explanations

    words related to geographical features

    oai_token-act-pair · gemini-2.0-flash

    mountain or hill

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    anky
    -0.51
     LCCN
    -0.47
     désolés
    -0.47
     słod
    -0.47
     kwam
    -0.47
     dedo
    -0.46
     secas
    -0.46
     puissante
    -0.46
     شیرین
    -0.45
     gerecht
    -0.45
    POSITIVE LOGITS
     autorytatywna
    0.84
     nakalista
    0.75
    Hochspringen
    0.74
    PerformLayout
    0.71
    #+#
    0.70
     UnityEditor
    0.69
     EClass
    0.67
     հղումներ
    0.63
    FormTagHelper
    0.62
     خارجية
    0.62
    Activations Density 1.078%

    No Known Activations