INDEX

Explanations

code-related keywords, particularly those related to validation and definition of data structures and requirements

oai_token-act-pair · gemini-2.0-flash

required

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

 gynhyrchwyd

-0.72

PyExc

-0.65

WithIOException

-0.62

éndolo

-0.60

MarshalTo

-0.57

TypedDataSet

-0.54

 متعلقه

-0.53

 parseFrom

-0.52

endencies

-0.52

RegistryLite

-0.52

POSITIVE LOGITS

 cubiertos

0.54

abestanden

0.54

addHandler

0.52

 greco

0.51

bürger

0.49

 datter

0.48

tableFuture

0.48

 darbo

0.48

 doInBackground

0.48

 contextLoads

0.47

Activations Density 0.165%

code-related keywords, particularly those related to validation and definition of data structures and requirements

required

No Comments

No Known Activations