INDEX

Explanations

words that suggest consideration or evaluation

oai_token-act-pair · gemini-2.0-flash

consider

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

)");

-0.66

Πηγή

-0.64

 Majefty

-0.60

blauch

-0.55

 becauſe

-0.55

)";

-0.50

 campagna

-0.50

 kayo

-0.50

 Houſe

-0.50

 ſeveral

-0.49

POSITIVE LOGITS

StoryboardSegue

0.87

 kasarigan

0.80

 transfieras

0.75

elemField

0.73

 Walkover

0.71

GraphicsUnit

0.70

 IndexPath

0.64

rungsseite

0.62

 Infórmanos

0.62

IVEREF

0.61

Activations Density 16.332%

words that suggest consideration or evaluation

consider

No Comments

No Known Activations