© 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. 14694
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with metals or metallic objects

    oai_token-act-pair · gemini-2.0-flash

    Mentions metal-related words

    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
     metal
    -2.53
     Metal
    -2.36
    Metal
    -2.28
    metal
    -2.28
     METAL
    -2.16
     steel
    -2.09
     Steel
    -2.02
    METAL
    -1.97
     metallic
    -1.95
     iron
    -1.92
    POSITIVE LOGITS
    ieteur
    0.59
     vân
    0.47
    klär
    0.45
     dòng
    0.44
     pager
    0.43
    НИК
    0.43
     Guilford
    0.42
    viser
    0.42
     Dorf
    0.42
    Captor
    0.42
    Activations Density 2.624%

    No Known Activations