INDEX

Explanations

statistical data, including confidence intervals, percentages, and p-values

oai_token-act-pair · gemini-2.0-flash

numbers between ten and twenty

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

$.

-0.69

 سكانية

-0.68

]";

-0.64

standers

-0.63

")));

-0.62

rogels

-0.59

ressee

-0.58

postolic

-0.57

__":

-0.57

eleste

-0.57

POSITIVE LOGITS

ten

0.68

 eleven

0.67

 Seventeen

0.61

 twenty

0.59

 thirteen

0.59

 Sixteen

0.58

 seventeen

0.57

 nine

0.57

 fifteen

0.57

 Fifteen

0.56

Activations Density 9.884%

statistical data, including confidence intervals, percentages, and p-values

numbers between ten and twenty

No Comments

No Known Activations