INDEX

Explanations

numbers, punctuation, and special characters within or next to words.

oai_token-act-pair · 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

th

-0.82

nd

-0.75

rd

-0.72

st

-0.69

ArgsConstructor

-0.64

bootstrapcdn

-0.62

″

-0.62

월

-0.56

 defaultstate

-0.56

个

-0.54

POSITIVE LOGITS

ſelf

0.60

utives

0.59

orna

0.57

SharedDtor

0.57

MessageTagHelper

0.57

UMENTS

0.56

 lenker

0.56

inerary

0.56

xiety

0.56

 Савезне

0.55

Activations Density 14.500%

numbers, punctuation, and special characters within or next to words.

No Comments

No Known Activations