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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 13218
    Prev
    Next
    INDEX
    Explanations

    demonstrative pronouns that show location

    oai_token-act-pair · gemini-2.0-flash

    these

    np_max-act-logits · gemini-2.0-flash

    these Method used: 1 — because the top tokens are all "these"

    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
     have
    -1.09
    have
    -1.02
    Have
    -1.00
     Have
    -1.00
     HAVE
    -0.91
    appear
    -0.83
    HAVE
    -0.82
     haben
    -0.81
     were
    -0.79
     Were
    -0.79
    POSITIVE LOGITS
    apnews
    0.56
    nosaurus
    0.55
     snippetHide
    0.54
    principalColumn
    0.54
    XmlSchema
    0.50
    RTEX
    0.49
    SBATCH
    0.48
    aroos
    0.47
    pannt
    0.47
    ITHUB
    0.47
    Activations Density 5.254%

    No Known Activations