INDEX

Explanations

the word 'range' and nearby words suggesting variety or measurement, especially 'wide'

oai_token-act-pair · gemini-2.0-flash

range

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

 range

-2.95

range

-2.55

 Range

-2.44

Range

-2.42

 RANGE

-2.30

 ranges

-2.20

RANGE

-2.08

 Ranges

-1.77

ranges

-1.75

 ranged

-1.59

POSITIVE LOGITS

ModelAdmin

0.71

 BorderRadius

0.69

twimg

0.66

MENAFN

0.63

principalColumn

0.63

oplayer

0.63

AutoScaleMode

0.59

titleMargin

0.58

Referanser

0.57

 resourceCulture

0.57

Activations Density 4.550%

the word 'range' and nearby words suggesting variety or measurement, especially 'wide'

range

No Comments

No Known Activations