INDEX

Explanations

text referencing both newspapers and royalty

oai_token-act-pair · gemini-2.0-flash

Royalty

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

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

 royal

-2.36

 Royal

-2.20

royal

-2.14

 ROYAL

-2.11

Royal

-2.09

 King

-2.08

 king

-2.06

 KING

-2.05

 Kings

-1.99

 queen

-1.98

POSITIVE LOGITS

 Spra

0.47

 Tempe

0.45

 Gord

0.42

WriteTagHelper

0.42

).—

0.41

 Debre

0.40

ducción

0.40

 Hibernate

0.39

 ffilmiau

0.39

noscript

0.38

Activations Density 1.339%

text referencing both newspapers and royalty

Royalty

No Comments

No Known Activations