INDEX

Explanations

lists and numerical data

oai_token-act-pair · gemini-2.0-flash

Information related concepts

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

 CreateTagHelper

-0.69

GraphicsUnit

-0.65

enumi

-0.65

MemoryWarning

-0.64

 ISNI

-0.56

RegressionTest

-0.55

bootstrapcdn

-0.54

IContainer

-0.52

actionMode

-0.50

VIAF

-0.50

POSITIVE LOGITS

 stuff

1.30

 legislation

1.20

 evidence

1.17

 information

1.06

evidence

1.05

stuff

1.02

legislation

1.02

 STUFF

0.99

 Stuff

0.99

 equipment

0.99

Activations Density 6.170%

lists and numerical data

Information related concepts

No Comments

No Known Activations