INDEX

Explanations

code snippets with elements like arrays, header functions and POST requests

oai_token-act-pair · gemini-2.0-flash

code and databases

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.71

-0.59

-0.54

ese

-0.54

-0.53

-0.52

POSITIVE LOGITS

parsedMessage

1.16

RenderAtEndOf

1.13

 مشين

1.09

 Roskov

1.09

UrlResolution

1.07

 дописавши

1.05

AccessorTable

1.02

存于互联网档案馆

1.01

 autorytatywna

1.01

 Савезне

1.00

Activations Density 2.095%

code snippets with elements like arrays, header functions and POST requests

code and databases

No Comments

No Known Activations