INDEX

Explanations

LaTeX commands, especially those for including packages and defining document structure

oai_token-act-pair · gemini-2.0-flash

Code and scientific text

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

 fragmentation

-0.47

 Dage

-0.46

umos

-0.46

slidesPer

-0.45

oprot

-0.45

仕

-0.43

 Cardinale

-0.41

}^{+}\

-0.41

 fers

-0.41

 Digital

-0.40

POSITIVE LOGITS

存于互联网档案馆

0.77

 esternos

0.70

AddTagHelper

0.65

featureID

0.65

WEBPACK

0.64

[\

0.63

enumi

0.61

 HasFactory

0.58

[%

0.58

[^

0.57

Activations Density 0.122%

LaTeX commands, especially those for including packages and defining document structure

Code and scientific text

No Comments

No Known Activations