© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 16055
    Prev
    Next
    INDEX
    Explanations

    mentions of the chemical element iron, 'Fe', sometimes next to a pronoun

    oai_token-act-pair · gemini-2.0-flash

    Fe

    np_max-act-logits · 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
    a
    -0.64
    ah
    -0.63
    aren
    -0.62
    ae
    -0.62
    able
    -0.60
    ab
    -0.60
    ls
    -0.59
    ak
    -0.58
    w
    -0.57
    ach
    -0.56
    POSITIVE LOGITS
    principalTable
    0.63
    bootstrapcdn
    0.52
    OGND
    0.52
     parseFrom
    0.47
    Przypisy
    0.45
    gers
    0.45
    gus
    0.44
    apimachinery
    0.44
    gic
    0.44
    gga
    0.43
    Activations Density 1.776%

    No Known Activations