INDEX

Explanations

XML-like tags, especially `</delim>`, `</match>`, `</read>`, `</write>`, `<data>`, and similar tags, and seems to give a higher activation to `</delim>`. In addition, the activation value increases depending on the number of end tags it finds in a

oai_token-act-pair · gemini-2.0-flash

delim

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

Efq

-0.86

 itſelf

-0.84

 Jefus

-0.79

 uſed

-0.76

 Anſ

-0.75

 themſelves

-0.74

 himſelf

-0.73

 myſelf

-0.72

 poffible

-0.72

 Reſ

-0.72

POSITIVE LOGITS

>--}}

0.52

 high

0.47

 double

0.47

 counter

0.46

</em>

0.45

ParallelGroup

0.44

 return

0.43

 place

0.43

↵↵

0.43

↵

0.43

Activations Density 1.109%

XML-like tags, especially `</delim>`, `</match>`, `</read>`, `</write>`, `<data>`, and similar tags, and seems to give a higher activation to `</delim>`. In addition, the activation value increases depending on the number of end tags it finds in a

delim

No Comments

No Known Activations

XML-like tags, especially `</delim>`, `</match>`, `</read>`, `</write>`, `<data>`, and similar tags, and seems to give a higher activation to `</delim>`. In addition, the activation value increases depending on the number of end tags it finds in a

delim

No Comments

No Known Activations