© 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. 1311
    Prev
    Next
    INDEX
    Explanations

    the prefix "Mal" as part of a name or title

    oai_token-act-pair · gemini-2.0-flash

    Mal

    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
     EconPapers
    -0.77
    Tikang
    -0.71
     MainAxisSize
    -0.67
     getopt
    -0.63
     betweenstory
    -0.60
     Normdatei
    -0.59
    IsContent
    -0.59
     rospy
    -0.59
    Демографія
    -0.59
    AddTagHelper
    -0.57
    POSITIVE LOGITS
     chrétien
    0.57
     Juifs
    0.55
    loyed
    0.55
     vétérina
    0.54
    VALIDATE
    0.51
    mgren
    0.51
    conse
    0.50
     étrangère
    0.49
     végétal
    0.49
    transformation
    0.49
    Activations Density 3.430%

    No Known Activations