INDEX

Explanations

code snippets, particularly those containing hexidecimal values and numbers

oai_token-act-pair · gemini-2.0-flash

code

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

IsContent

-0.94

TagMode

-0.88

EDEFAULT

-0.82

 initComponents

-0.82

 שוליים

-0.81

 &___

-0.76

Externí

-0.74

PreferredItem

-0.73

VIAF

-0.69

+#+#

-0.69

POSITIVE LOGITS

SPECIFIED

0.46

ID

0.45

 maybe

0.44

 perhaps

0.44

 defectos

0.44

 nice

0.44

Gentlemen

0.43

qid

0.43

urm

0.42

werks

0.41

Activations Density 2.142%

code snippets, particularly those containing hexidecimal values and numbers

code

No Comments

No Known Activations