INDEX

Explanations

href

np_max-act-logits · gemini-2.0-flash

HTML code related to hyperlinks and targets

oai_token-act-pair · gemini-2.0-flash

href

np_token-act-pair-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_16/width_16k/average_l0_10

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 mecán

-0.50

 complètes

-0.49

 chimiques

-0.49

 mecánico

-0.48

genossen

-0.48

Rex

-0.47

dotti

-0.47

 espirituales

-0.47

 extranjero

-0.47

หนึ่ง

-0.46

POSITIVE LOGITS

########.

0.98

IBOutlet

0.91

 ProtoMessage

0.85

contentLoaded

0.85

ScopeManager

0.82

 hObject

0.80

 MainAxisSize

0.77

WriteTagHelper

0.77

InjectAttribute

0.73

 resourceCulture

0.73

Activations Density 0.812%

href

HTML code related to hyperlinks and targets

href

No Comments

No Known Activations