INDEX

Explanations

Code

np_max-act-logits · gemini-2.0-flash

code syntax such as comparison operators, parentheses, and brackets

oai_token-act-pair · gemini-2.0-flash

code snippets containing `err`

np_token-act-pair-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_16/width_16k/average_l0_10

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

AndEndTag

-0.72

 smtplib

-0.67

gonic

-0.67

 gäller

-0.67

ClientSize

-0.65

rrggbb

-0.65

contentLoaded

-0.64

 ddelweddau

-0.64

źć

-0.63

batore

-0.63

POSITIVE LOGITS

`;

0.52

 thức

0.43

";

0.42

かわらず

0.42

intahan

0.41

 inside

0.41

.";

0.41

")]

0.40

.");

0.39

PostExecute

0.39

Activations Density 0.291%

Code

code syntax such as comparison operators, parentheses, and brackets

code snippets containing `err`

No Comments

No Known Activations