© 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. 5745
    Prev
    Next
    INDEX
    Explanations

    the word "redstone" especially when near words like "torch," "powered," or "rail."

    oai_token-act-pair · gemini-2.0-flash

    foreign 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
    хьтан
    -0.90
    IndentedString
    -0.80
    complexContent
    -0.73
     snippetHide
    -0.66
     referrerpolicy
    -0.66
    彿
    -0.61
     esternos
    -0.60
     iprot
    -0.60
     صوتيه
    -0.59
     PIA
    -0.59
    POSITIVE LOGITS
     malheure
    0.55
     malheureux
    0.47
     dimentic
    0.46
     mă
    0.45
     dimenti
    0.42
     Creature
    0.42
     diluted
    0.42
    extrême
    0.42
     bū
    0.42
     espectro
    0.41
    Activations Density 1.829%

    No Known Activations