INDEX

Explanations

text describing some sort of written inscription on a physical object

oai_token-act-pair · gemini-2.0-flash

writing utensils

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

 للاسماء

-0.87

хьтан

-0.82

évaluateur

-0.79

 متعلقه

-0.69

تفصیلات

-0.66

 Ouverture

-0.66

 relatifs

-0.65

webElementXpaths

-0.64

रीदारी

-0.62

 Италијани

-0.62

POSITIVE LOGITS

pen

1.47

ink

1.29

 pens

1.29

 pencil

1.20

 marker

1.20

Pen

1.16

pen

1.13

 Pens

1.09

Pen

1.09

 markers

1.05

Activations Density 0.757%

text describing some sort of written inscription on a physical object

writing utensils

No Comments

No Known Activations