© 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. 3940
    Prev
    Next
    INDEX
    Explanations

    pieces of documentation about weather

    oai_token-act-pair · gemini-2.0-flash

    /** - because previous methods failed to reveal a good answer

    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
     "/")
    -0.60
     gentes
    -0.59
     EconPapers
    -0.59
     goederen
    -0.58
     vettore
    -0.57
     voire
    -0.57
     hiszen
    -0.57
     gesteld
    -0.57
     "$
    -0.57
     scorso
    -0.56
    POSITIVE LOGITS
     تضيفلها
    0.56
    StoreMessageInfo
    0.49
     interak
    0.45
    principalColumn
    0.45
     Kont
    0.45
    styleType
    0.44
     Langmuir
    0.43
    typeparam
    0.43
    databinding
    0.43
    MTL
    0.43
    Activations Density 0.585%

    No Known Activations