INDEX

Explanations

file paths and the words "report" and "planner."

oai_token-act-pair · gemini-2.0-flash

say numbers

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

 myſelf

-1.23

 فريبيس

-1.06

Efq

-1.05

 Theſe

-1.03

 betweenstory

-1.01

 Monfieur

-1.00

StoryboardSegue

-0.99

 avoient

-0.98

 GenerationType

-0.98

 themſelves

-0.94

POSITIVE LOGITS

0.53

0.52

0.51

<bos>

0.50

0.49

0.48

0.47

 pres

0.44

Activations Density 9.203%

file paths and the words "report" and "planner."

say numbers

No Comments

No Known Activations