INDEX

Explanations

Java-related code, specifically code that uses the Java Native Interface (JNI)

oai_token-act-pair · gemini-2.0-flash

jni

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

مصادر

-0.55

<tbody>

-0.49

"/></

-0.48

 initComponents

-0.47

/">

-0.47

achal

-0.45

GIVEREF

-0.44



-0.43

[*]

-0.42

Zen

-0.42

POSITIVE LOGITS

 profondeur

0.69

thâu

0.68

المكان

0.64

 pauv

0.60

 épis

0.60

 للاسماء

0.59

 étoient

0.59

 avoient

0.58

 démocr

0.58

tagHelperRunner

0.57

Activations Density 2.115%

Java-related code, specifically code that uses the Java Native Interface (JNI)

jni

No Comments

No Known Activations