© 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. 8867
    Prev
    Next
    INDEX
    Explanations

    words describing chemical bonds and interactions

    oai_token-act-pair · gemini-2.0-flash

    Chemical bonds

    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
    AddTagHelper
    -0.90
    #+#
    -0.83
     lenker
    -0.83
    الحياه
    -0.82
     AssemblyCulture
    -0.81
    Personendaten
    -0.80
    Rüyada
    -0.79
    хьтан
    -0.78
     initComponents
    -0.74
    Gweler
    -0.71
    POSITIVE LOGITS
     equilateral
    0.47
    bonucle
    0.46
     concentric
    0.46
     transistors
    0.43
     covalent
    0.42
     mechanistic
    0.41
     bromide
    0.40
     amplitude
    0.40
     alkaline
    0.40
     algebraic
    0.40
    Activations Density 9.802%

    No Known Activations