INDEX

Explanations

words and phrases related to complex data analysis and comparisons of measured values.

oai_token-act-pair · gemini-2.0-flash

lower/upper

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

mybatisplus

-0.63

longer

-0.62

достатки

-0.61

UrlResolution

-0.60

DockStyle

-0.60

Bioaccumulative

-0.59

 bigger

-0.58

 Larger

-0.57

μφωνα

-0.57

cshtml

-0.56

POSITIVE LOGITS

 lower

2.22

 Lower

1.89

Lower

1.87

lower

1.81

 LOWER

1.66

LOWER

1.30

 ниж

0.96

 upper

0.93

 Upper

0.92

Upper

0.91

Activations Density 13.501%

words and phrases related to complex data analysis and comparisons of measured values.

lower/upper

No Comments

No Known Activations