© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 5931
    Prev
    Next
    INDEX
    Explanations

    words indicating locations and their relationship to things

    oai_token-act-pair · gemini-2.0-flash

    French words

    np_max-act-logits · gemini-2.0-flash

    in

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     Philist
    -0.86
     Malawi
    -0.82
    phosa
    -0.80
    WebControls
    -0.79
     Vanuatu
    -0.79
     Peshawar
    -0.76
    ंदीखरीदारी
    -0.76
     Lusaka
    -0.75
     Burundi
    -0.75
     Uganda
    -0.75
    POSITIVE LOGITS
     fondament
    0.54
     fédé
    0.54
     sanitaires
    0.51
     refusé
    0.49
     étro
    0.49
     énergé
    0.48
     numériques
    0.48
     religieuses
    0.48
     décédé
    0.47
     banderas
    0.47
    Activations Density 17.662%

    No Known Activations