INDEX

Explanations

words and phrases describing connection in different contexts, whether personal, professional, or spiritual.

oai_token-act-pair · gemini-2.0-flash

interpersonal relationships

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

-1.00

TagMode

-0.93

 muualla

-0.89

StoryboardSegue

-0.85

 виправивши

-0.85

 وتسجيلات

-0.84

 raiſ

-0.83

ніципалі

-0.83

 للمعارف

-0.79

 Shakspeare

-0.79

POSITIVE LOGITS

att

0.46

</

0.46

•

0.45

 råd

0.43

WriteLiteral

0.42

 each

0.41

·

0.41

File

0.40

 hver

0.40

 bety

0.38

Activations Density 2.336%

words and phrases describing connection in different contexts, whether personal, professional, or spiritual.

interpersonal relationships

No Comments

No Known Activations