© 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. 25-GEMMASCOPE-TRANSCODER-16K
    4. 944
    Prev
    Next
    INDEX
    Explanations

    the pronoun 'it', and sometimes 'he', in the context of an explanation

    oai_token-act-pair · gemini-2.0-flash
    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
     need
    -2.67
    need
    -2.39
     Need
    -2.28
    Need
    -2.22
     NEED
    -1.91
    NEED
    -1.75
     necesidad
    -1.52
     besoin
    -1.39
     behöver
    -1.27
     necessidade
    -1.27
    POSITIVE LOGITS
     autorytatywna
    0.76
    ipedi
    0.66
     Exactos
    0.60
     internetowa
    0.57
     utafitiHapana
    0.56
    Hochspringen
    0.54
    Externe
    0.53
    webElementGuid
    0.52
    ExecuteReader
    0.51
     Chwiliwch
    0.50
    Activations Density 7.053%

    No Known Activations